Machine learning (ML) is a field of inquiry devoted to understanding and building methods that 'learn', that is, methods that leverage data to improve performance on some set of tasks. It is seen as a part of
artificial intelligence
Artificial intelligence (AI) is intelligence—perceiving, synthesizing, and inferring information—demonstrated by machines, as opposed to intelligence displayed by animals and humans. Example tasks in which this is done include speech r ...
.
Machine learning algorithms build a model based on sample data, known as
training data
In machine learning, a common task is the study and construction of algorithms that can learn from and make predictions on data. Such algorithms function by making data-driven predictions or decisions, through building a mathematical model from ...
, in order to make predictions or decisions without being explicitly programmed to do so. Machine learning algorithms are used in a wide variety of applications, such as in medicine,
email filtering
Email filtering is the processing of email to organize it according to specified criteria. The term can apply to the intervention of human intelligence, but most often refers to the automatic processing of messages at an SMTP server, possibly appl ...
,
speech recognition
Speech recognition is an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enable the recognition and translation of spoken language into text by computers with the ...
,
agriculture
Agriculture or farming is the practice of cultivating plants and livestock. Agriculture was the key development in the rise of sedentary human civilization, whereby farming of domesticated species created food surpluses that enabled people t ...
, and
computer vision, where it is difficult or unfeasible to develop conventional algorithms to perform the needed tasks.
[Hu, J.; Niu, H.; Carrasco, J.; Lennox, B.; Arvin, F.,]
Voronoi-Based Multi-Robot Autonomous Exploration in Unknown Environments via Deep Reinforcement Learning
IEEE Transactions on Vehicular Technology, 2020.
A subset of machine learning is closely related to
computational statistics
Computational statistics, or statistical computing, is the bond between statistics and computer science. It means statistical methods that are enabled by using computational methods. It is the area of computational science (or scientific computin ...
, which focuses on making predictions using computers, but not all machine learning is statistical learning. The study of
mathematical optimization delivers methods, theory and application domains to the field of machine learning.
Data mining is a related field of study, focusing on
exploratory data analysis
In statistics, exploratory data analysis (EDA) is an approach of analyzing data sets to summarize their main characteristics, often using statistical graphics and other data visualization methods. A statistical model can be used or not, but pri ...
through
unsupervised learning
Unsupervised learning is a type of algorithm that learns patterns from untagged data. The hope is that through mimicry, which is an important mode of learning in people, the machine is forced to build a concise representation of its world and t ...
.
Some implementations of machine learning use data and
neural networks in a way that mimics the working of a
biological brain.
In its application across business problems, machine learning is also referred to as
predictive analytics
Predictive analytics encompasses a variety of statistical techniques from data mining, predictive modeling, and machine learning that analyze current and historical facts to make predictions about future or otherwise unknown events.
In busine ...
.
Overview
Learning algorithms work on the basis that strategies, algorithms, and inferences that worked well in the past are likely to continue working well in the future. These inferences can be obvious, such as "since the sun rose every morning for the last 10,000 days, it will probably rise tomorrow morning as well". They can be nuanced, such as "X% of
families
Family (from la, familia) is a group of people related either by consanguinity (by recognized birth) or affinity (by marriage or other relationship). The purpose of the family is to maintain the well-being of its members and of society. Ideal ...
have geographically separate species with color variants, so there is a Y% chance that undiscovered
black swans Black swan is the common name for ''Cygnus atratus'', an Australasian waterfowl.
(The) Black Swan(s) may also refer to:
Film and television
* ''The Black Swan'' (film), a 1942 swashbuckler film
* ''Black Swans'' (film), a 2005 Dutch drama film
* ...
exist".
Machine learning programs can perform tasks without being explicitly programmed to do so. It involves computers learning from data provided so that they carry out certain tasks. For simple tasks assigned to computers, it is possible to program algorithms telling the machine how to execute all steps required to solve the problem at hand; on the computer's part, no learning is needed. For more advanced tasks, it can be challenging for a human to manually create the needed algorithms. In practice, it can turn out to be more effective to help the machine develop its own algorithm, rather than having human programmers specify every needed step.
The discipline of machine learning employs various approaches to teach computers to accomplish tasks where no fully satisfactory algorithm is available. In cases where vast numbers of potential answers exist, one approach is to label some of the correct answers as valid. This can then be used as training data for the computer to improve the algorithm(s) it uses to determine correct answers. For example, to train a system for the task of digital character recognition, the
MNIST dataset of handwritten digits has often been used.
History and relationships to other fields
The term ''machine learning'' was coined in 1959 by
Arthur Samuel
Arthur Lee Samuel (December 5, 1901 – July 29, 1990) was an American pioneer in the field of computer gaming and artificial intelligence. He popularized the term "machine learning" in 1959. The Samuel Checkers-playing Program was among the wo ...
, an
IBM employee and pioneer in the field of
computer gaming
A personal computer game, also known as a PC game or computer game, is a type of video game played on a personal computer (PC) rather than a video game console or arcade machine. Its defining characteristics include: more diverse and user-deter ...
and
artificial intelligence
Artificial intelligence (AI) is intelligence—perceiving, synthesizing, and inferring information—demonstrated by machines, as opposed to intelligence displayed by animals and humans. Example tasks in which this is done include speech r ...
.
The synonym ''self-teaching computers'' was also used in this time period.
By the early 1960s an experimental "learning machine" with
punched tape
Five- and eight-hole punched paper tape
Paper tape reader on the Harwell computer with a small piece of five-hole tape connected in a circle – creating a physical program loop
Punched tape or perforated paper tape is a form of data storage ...
memory, called Cybertron, had been developed by
Raytheon Company
The Raytheon Company was a major U.S. defense contractor and industrial corporation with manufacturing concentrations in weapons and military and commercial electronics. It was previously involved in corporate and special-mission aircraft unti ...
to analyze sonar signals, electrocardiograms, and speech patterns using rudimentary
reinforcement learning
Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine ...
. It was repetitively "trained" by a human operator/teacher to recognize patterns and equipped with a "
goof
A goof is a mistake. The term is also used in a number of specific senses: in cinema, it is an error or oversight during production that is visible in the released version of the film.
Etymology
Several origins have been proposed for the word. ...
" button to cause it to re-evaluate incorrect decisions. A representative book on research into machine learning during the 1960s was Nilsson's book on Learning Machines, dealing mostly with machine learning for pattern classification. Interest related to pattern recognition continued into the 1970s, as described by Duda and Hart in 1973. In 1981 a report was given on using teaching strategies so that a
neural network learns to recognize 40 characters (26 letters, 10 digits, and 4 special symbols) from a computer terminal.
Tom M. Mitchell provided a widely quoted, more formal definition of the algorithms studied in the machine learning field: "A computer program is said to learn from experience ''E'' with respect to some class of tasks ''T'' and performance measure ''P'' if its performance at tasks in ''T'', as measured by ''P'', improves with experience ''E''."
This definition of the tasks in which machine learning is concerned offers a fundamentally
operational definition
An operational definition specifies concrete, replicable procedures designed to represent a construct. In the words of American psychologist S.S. Stevens (1935), "An operation is the performance which we execute in order to make known a concept." F ...
rather than defining the field in cognitive terms. This follows
Alan Turing
Alan Mathison Turing (; 23 June 1912 – 7 June 1954) was an English mathematician, computer scientist, logician, cryptanalyst, philosopher, and theoretical biologist. Turing was highly influential in the development of theoretical co ...
's proposal in his paper "
Computing Machinery and Intelligence
"Computing Machinery and Intelligence" is a seminal paper written by Alan Turing on the topic of artificial intelligence. The paper, published in 1950 in ''Mind'', was the first to introduce his concept of what is now known as the Turing test to ...
", in which the question "Can machines think?" is replaced with the question "Can machines do what we (as thinking entities) can do?".
Modern-day machine learning has two objectives, one is to classify data based on models which have been developed, the other purpose is to make predictions for future outcomes based on these models. A hypothetical algorithm specific to classifying data may use computer vision of moles coupled with supervised learning in order to train it to classify the cancerous moles. A machine learning algorithm for stock trading may inform the trader of future potential predictions.
Artificial intelligence
![Fig-y_Part_of_ML_as_subfield_of_AI_or_AI_as_subfield_of_ML](https://upload.wikimedia.org/wikipedia/commons/2/23/Fig-y_Part_of_ML_as_subfield_of_AI_or_AI_as_subfield_of_ML.jpg)
As a scientific endeavor, machine learning grew out of the quest for artificial intelligence. In the early days of AI as an
academic discipline
An academy (Attic Greek: Ἀκαδήμεια; Koine Greek Ἀκαδημία) is an institution of secondary or tertiary higher learning (and generally also research or honorary membership). The name traces back to Plato's school of philosophy, ...
, some researchers were interested in having machines learn from data. They attempted to approach the problem with various symbolic methods, as well as what was then termed "
neural networks"; these were mostly
perceptron
In machine learning, the perceptron (or McCulloch-Pitts neuron) is an algorithm for supervised learning of binary classifiers. A binary classifier is a function which can decide whether or not an input, represented by a vector of numbers, belon ...
s and
other models that were later found to be reinventions of the
generalized linear models of statistics.
Probabilistic reasoning Probabilistic logic (also probability logic and probabilistic reasoning) involves the use of probability and logic to deal with uncertain situations. Probabilistic logic extends traditional logic truth tables with probabilistic expressions. A diffic ...
was also employed, especially in
automated medical diagnosis
Computer-aided detection (CADe), also called computer-aided diagnosis (CADx), are systems that assist doctors in the interpretation of medical images. Imaging techniques in X-ray, MRI, Endoscopy, and ultrasound diagnostics yield a great deal o ...
.
However, an increasing emphasis on the
logical, knowledge-based approach caused a rift between AI and machine learning. Probabilistic systems were plagued by theoretical and practical problems of data acquisition and representation.
By 1980,
expert systems had come to dominate AI, and statistics was out of favor.
Work on symbolic/knowledge-based learning did continue within AI, leading to
inductive logic programming, but the more statistical line of research was now outside the field of AI proper, in
pattern recognition
Pattern recognition is the automated recognition of patterns and regularities in data. It has applications in statistical data analysis, signal processing, image analysis, information retrieval, bioinformatics, data compression, computer graphics ...
and
information retrieval.
Neural networks research had been abandoned by AI and
computer science
Computer science is the study of computation, automation, and information. Computer science spans theoretical disciplines (such as algorithms, theory of computation, information theory, and automation) to practical disciplines (includi ...
around the same time. This line, too, was continued outside the AI/CS field, as "
connectionism
Connectionism refers to both an approach in the field of cognitive science that hopes to explain mental phenomena using artificial neural networks (ANN) and to a wide range of techniques and algorithms using ANNs in the context of artificial in ...
", by researchers from other disciplines including
Hopfield,
Rumelhart, and
Hinton. Their main success came in the mid-1980s with the reinvention of
backpropagation
In machine learning, backpropagation (backprop, BP) is a widely used algorithm for training feedforward artificial neural networks. Generalizations of backpropagation exist for other artificial neural networks (ANNs), and for functions gener ...
.
Machine learning (ML), reorganized as a separate field, started to flourish in the 1990s. The field changed its goal from achieving artificial intelligence to tackling solvable problems of a practical nature. It shifted focus away from the
symbolic approaches it had inherited from AI, and toward methods and models borrowed from statistics,
fuzzy logic, and
probability theory
Probability theory is the branch of mathematics concerned with probability. Although there are several different probability interpretations, probability theory treats the concept in a rigorous mathematical manner by expressing it through a set ...
.
The difference between ML and AI is frequently misunderstood. ML learns and predicts based on passive observations, whereas AI implies an agent interacting with the environment to learn and take actions that maximize its chance of successfully achieving its goals.
As of 2020, many sources continue to assert that ML remains a subfield of AI.
Others have the view that not all ML is part of AI, but only an 'intelligent subset' of ML should be considered AI.
Data mining
Machine learning and
data mining often employ the same methods and overlap significantly, but while machine learning focuses on prediction, based on ''known'' properties learned from the training data,
data mining focuses on the
discovery
Discovery may refer to:
* Discovery (observation), observing or finding something unknown
* Discovery (fiction), a character's learning something unknown
* Discovery (law), a process in courts of law relating to evidence
Discovery, The Discover ...
of (previously) ''unknown'' properties in the data (this is the analysis step of
knowledge discovery
Knowledge extraction is the creation of knowledge from structured (relational databases, XML) and unstructured (text, documents, images) sources. The resulting knowledge needs to be in a machine-readable and machine-interpretable format and must r ...
in databases). Data mining uses many machine learning methods, but with different goals; on the other hand, machine learning also employs data mining methods as "unsupervised learning" or as a preprocessing step to improve learner accuracy. Much of the confusion between these two research communities (which do often have separate conferences and separate journals,
ECML PKDD being a major exception) comes from the basic assumptions they work with: in machine learning, performance is usually evaluated with respect to the ability to ''reproduce known'' knowledge, while in knowledge discovery and data mining (KDD) the key task is the discovery of previously ''unknown'' knowledge. Evaluated with respect to known knowledge, an uninformed (unsupervised) method will easily be outperformed by other supervised methods, while in a typical KDD task, supervised methods cannot be used due to the unavailability of training data.
Optimization
Machine learning also has intimate ties to
optimization
Mathematical optimization (alternatively spelled ''optimisation'') or mathematical programming is the selection of a best element, with regard to some criterion, from some set of available alternatives. It is generally divided into two subfi ...
: many learning problems are formulated as minimization of some
loss function on a training set of examples. Loss functions express the discrepancy between the predictions of the model being trained and the actual problem instances (for example, in classification, one wants to assign a label to instances, and models are trained to correctly predict the pre-assigned labels of a set of examples).
Generalization
The difference between optimization and machine learning arises from the goal of generalization: while optimization algorithms can minimize the loss on a training set, machine learning is concerned with minimizing the loss on unseen samples. Characterizing the generalization of various learning algorithms is an active topic of current research, especially for
deep learning algorithms.
Statistics
Machine learning and
statistics are closely related fields in terms of methods, but distinct in their principal goal: statistics draws population
inferences
Inferences are steps in reasoning, moving from premises to logical consequences; etymologically, the word ''infer'' means to "carry forward". Inference is theoretically traditionally divided into deduction and induction, a distinction that in ...
from a
sample, while machine learning finds generalizable predictive patterns. According to
Michael I. Jordan, the ideas of machine learning, from methodological principles to theoretical tools, have had a long pre-history in statistics.
He also suggested the term
data science as a placeholder to call the overall field.
Leo Breiman distinguished two statistical modeling paradigms: data model and algorithmic model,
wherein "algorithmic model" means more or less the machine learning algorithms like
Random forest.
Some statisticians have adopted methods from machine learning, leading to a combined field that they call ''statistical learning''.
Theory
A core objective of a learner is to generalize from its experience.
Generalization in this context is the ability of a learning machine to perform accurately on new, unseen examples/tasks after having experienced a learning data set. The training examples come from some generally unknown probability distribution (considered representative of the space of occurrences) and the learner has to build a general model about this space that enables it to produce sufficiently accurate predictions in new cases.
The computational analysis of machine learning algorithms and their performance is a branch of
theoretical computer science
computer science (TCS) is a subset of general computer science and mathematics that focuses on mathematical aspects of computer science such as the theory of computation, lambda calculus, and type theory.
It is difficult to circumscribe the ...
known as
computational learning theory
In computer science, computational learning theory (or just learning theory) is a subfield of artificial intelligence devoted to studying the design and analysis of machine learning algorithms.
Overview
Theoretical results in machine learning m ...
via the
Probably Approximately Correct Learning
In computational learning theory, probably approximately correct (PAC) learning is a framework for mathematical analysis of machine learning. It was proposed in 1984 by Leslie Valiant.L. Valiant. A theory of the learnable.' Communications of the ...
(PAC) model. Because training sets are finite and the future is uncertain, learning theory usually does not yield guarantees of the performance of algorithms. Instead, probabilistic bounds on the performance are quite common. The
bias–variance decomposition is one way to quantify generalization
error
An error (from the Latin ''error'', meaning "wandering") is an action which is inaccurate or incorrect. In some usages, an error is synonymous with a mistake. The etymology derives from the Latin term 'errare', meaning 'to stray'.
In statistics ...
.
For the best performance in the context of generalization, the complexity of the hypothesis should match the complexity of the function underlying the data. If the hypothesis is less complex than the function, then the model has under fitted the data. If the complexity of the model is increased in response, then the training error decreases. But if the hypothesis is too complex, then the model is subject to
overfitting and generalization will be poorer.
In addition to performance bounds, learning theorists study the time complexity and feasibility of learning. In computational learning theory, a computation is considered feasible if it can be done in
polynomial time. There are two kinds of
time complexity
In computer science, the time complexity is the computational complexity that describes the amount of computer time it takes to run an algorithm. Time complexity is commonly estimated by counting the number of elementary operations performed by t ...
results: Positive results show that a certain class of functions can be learned in polynomial time. Negative results show that certain classes cannot be learned in polynomial time.
Approaches
Machine learning approaches are traditionally divided into three broad categories, which correspond to learning paradigms, depending on the nature of the "signal" or "feedback" available to the learning system:
*
Supervised learning
Supervised learning (SL) is a machine learning paradigm for problems where the available data consists of labelled examples, meaning that each data point contains features (covariates) and an associated label. The goal of supervised learning alg ...
: The computer is presented with example inputs and their desired outputs, given by a "teacher", and the goal is to learn a general rule that
maps
A map is a symbolic depiction emphasizing relationships between elements of some space, such as objects, regions, or themes.
Many maps are static, fixed to paper or some other durable medium, while others are dynamic or interactive. Although ...
inputs to outputs.
*
Unsupervised learning
Unsupervised learning is a type of algorithm that learns patterns from untagged data. The hope is that through mimicry, which is an important mode of learning in people, the machine is forced to build a concise representation of its world and t ...
: No labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end (
feature learning
In machine learning, feature learning or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature ...
).
*
Reinforcement learning
Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine ...
: A computer program interacts with a dynamic environment in which it must perform a certain goal (such as
driving a vehicle or playing a game against an opponent). As it navigates its problem space, the program is provided feedback that's analogous to rewards, which it tries to maximize.
Supervised learning
![Svm max sep hyperplane with margin](https://upload.wikimedia.org/wikipedia/commons/2/2a/Svm_max_sep_hyperplane_with_margin.png)
Supervised learning algorithms build a mathematical model of a set of data that contains both the inputs and the desired outputs. The data is known as
training data
In machine learning, a common task is the study and construction of algorithms that can learn from and make predictions on data. Such algorithms function by making data-driven predictions or decisions, through building a mathematical model from ...
, and consists of a set of training examples. Each training example has one or more inputs and the desired output, also known as a supervisory signal. In the mathematical model, each training example is represented by an
array
An array is a systematic arrangement of similar objects, usually in rows and columns.
Things called an array include:
{{TOC right
Music
* In twelve-tone and serial composition, the presentation of simultaneous twelve-tone sets such that the ...
or vector, sometimes called a feature vector, and the training data is represented by a
matrix. Through
iterative optimization of an
objective function
In mathematical optimization and decision theory, a loss function or cost function (sometimes also called an error function) is a function that maps an event or values of one or more variables onto a real number intuitively representing some "cost ...
, supervised learning algorithms learn a function that can be used to predict the output associated with new inputs. An optimal function will allow the algorithm to correctly determine the output for inputs that were not a part of the training data. An algorithm that improves the accuracy of its outputs or predictions over time is said to have learned to perform that task.
Types of supervised-learning algorithms include
active learning
Active learning is "a method of learning in which students are actively or experientially involved in the learning process and where there are different levels of active learning, depending on student involvement." states that "students partici ...
,
classification and
regression.
Classification algorithms are used when the outputs are restricted to a limited set of values, and regression algorithms are used when the outputs may have any numerical value within a range. As an example, for a classification algorithm that filters emails, the input would be an incoming email, and the output would be the name of the folder in which to file the email.
Similarity learning is an area of supervised machine learning closely related to regression and classification, but the goal is to learn from examples using a similarity function that measures how similar or related two objects are. It has applications in
ranking
A ranking is a relationship between a set of items such that, for any two items, the first is either "ranked higher than", "ranked lower than" or "ranked equal to" the second.
In mathematics, this is known as a weak order or total preorder of ...
,
recommendation systems, visual identity tracking, face verification, and speaker verification.
Unsupervised learning
Unsupervised learning algorithms take a set of data that contains only inputs, and find structure in the data, like grouping or clustering of data points. The algorithms, therefore, learn from test data that has not been labeled, classified or categorized. Instead of responding to feedback, unsupervised learning algorithms identify commonalities in the data and react based on the presence or absence of such commonalities in each new piece of data. A central application of unsupervised learning is in the field of
density estimation
In statistics, probability density estimation or simply density estimation is the construction of an estimate, based on observed data, of an unobservable underlying probability density function. The unobservable density function is thought of ...
in
statistics, such as finding the
probability density function
In probability theory, a probability density function (PDF), or density of a continuous random variable, is a function whose value at any given sample (or point) in the sample space (the set of possible values taken by the random variable) ca ...
.
Though unsupervised learning encompasses other domains involving summarizing and explaining data features.
Cluster analysis is the assignment of a set of observations into subsets (called ''clusters'') so that observations within the same cluster are similar according to one or more predesignated criteria, while observations drawn from different clusters are dissimilar. Different clustering techniques make different assumptions on the structure of the data, often defined by some ''similarity metric'' and evaluated, for example, by ''internal compactness'', or the similarity between members of the same cluster, and ''separation'', the difference between clusters. Other methods are based on ''estimated density'' and ''graph connectivity''.
Semi-supervised learning
Semi-supervised learning falls between
unsupervised learning
Unsupervised learning is a type of algorithm that learns patterns from untagged data. The hope is that through mimicry, which is an important mode of learning in people, the machine is forced to build a concise representation of its world and t ...
(without any labeled training data) and
supervised learning
Supervised learning (SL) is a machine learning paradigm for problems where the available data consists of labelled examples, meaning that each data point contains features (covariates) and an associated label. The goal of supervised learning alg ...
(with completely labeled training data). Some of the training examples are missing training labels, yet many machine-learning researchers have found that unlabeled data, when used in conjunction with a small amount of labeled data, can produce a considerable improvement in learning accuracy.
In
weakly supervised learning, the training labels are noisy, limited, or imprecise; however, these labels are often cheaper to obtain, resulting in larger effective training sets.
Reinforcement learning
Reinforcement learning is an area of machine learning concerned with how
software agent
In computer science, a software agent or software AI is a computer program that acts for a user or other program in a relationship of agency, which derives from the Latin ''agere'' (to do): an agreement to act on one's behalf. Such "action on beha ...
s ought to take
actions
Action may refer to:
* Action (narrative), a literary mode
* Action fiction, a type of genre fiction
* Action game, a genre of video game
Film
* Action film, a genre of film
* ''Action'' (1921 film), a film by John Ford
* ''Action'' (1980 fi ...
in an environment so as to maximize some notion of cumulative reward. Due to its generality, the field is studied in many other disciplines, such as
game theory,
control theory
Control theory is a field of mathematics that deals with the control of dynamical systems in engineered processes and machines. The objective is to develop a model or algorithm governing the application of system inputs to drive the system to a ...
,
operations research
Operations research ( en-GB, operational research) (U.S. Air Force Specialty Code: Operations Analysis), often shortened to the initialism OR, is a discipline that deals with the development and application of analytical methods to improve decis ...
,
information theory,
simulation-based optimization
Simulation-based optimization (also known as simply simulation optimization) integrates optimization techniques into simulation modeling and analysis. Because of the complexity of the simulation, the objective function may become difficult and expe ...
,
multi-agent system
A multi-agent system (MAS or "self-organized system") is a computerized system composed of multiple interacting intelligent agents.Hu, J.; Bhowmick, P.; Jang, I.; Arvin, F.; Lanzon, A.,A Decentralized Cluster Formation Containment Framework f ...
s,
swarm intelligence,
statistics and
genetic algorithms. In machine learning, the environment is typically represented as a
Markov decision process (MDP). Many reinforcement learning algorithms use
dynamic programming
Dynamic programming is both a mathematical optimization method and a computer programming method. The method was developed by Richard Bellman in the 1950s and has found applications in numerous fields, from aerospace engineering to economics. ...
techniques. Reinforcement learning algorithms do not assume knowledge of an exact mathematical model of the MDP, and are used when exact models are infeasible. Reinforcement learning algorithms are used in autonomous vehicles or in learning to play a game against a human opponent.
Dimensionality reduction
Dimensionality reduction is a process of reducing the number of random variables under consideration by obtaining a set of principal variables. In other words, it is a process of reducing the dimension of the feature set, also called the "number of features". Most of the dimensionality reduction techniques can be considered as either feature elimination or extraction.
One of the popular methods of dimensionality reduction is
principal component analysis (PCA). PCA involves changing higher-dimensional data (e.g., 3D) to a smaller space (e.g., 2D). This results in a smaller dimension of data (2D instead of 3D), while keeping all original variables in the model without changing the data.
The
manifold hypothesis proposes that high-dimensional data sets lie along low-dimensional
manifolds, and many dimensionality reduction techniques make this assumption, leading to the area of
manifold learning
Nonlinear dimensionality reduction, also known as manifold learning, refers to various related techniques that aim to project high-dimensional data onto lower-dimensional latent manifolds, with the goal of either visualizing the data in the low- ...
and
manifold regularization.
Other types
Other approaches have been developed which don't fit neatly into this three-fold categorization, and sometimes more than one is used by the same machine learning system. For example
topic modeling
In statistics and natural language processing, a topic model is a type of statistical model for discovering the abstract "topics" that occur in a collection of documents. Topic modeling is a frequently used text-mining tool for discovery of hidden ...
,
meta-learning
Meta-learning is a branch of metacognition concerned with learning about one's own learning and learning processes.
The term comes from the meta prefix's modern meaning of an abstract recursion, or "X about X", similar to its use in metaknowled ...
.
As of 2022,
deep learning is the dominant approach for much ongoing work in the field of machine learning.
Self-learning
Self-learning, as a machine learning paradigm was introduced in 1982 along with a neural network capable of self-learning, named ''crossbar adaptive array'' (CAA). It is learning with no external rewards and no external teacher advice. The CAA self-learning algorithm computes, in a crossbar fashion, both decisions about actions and emotions (feelings) about consequence situations. The system is driven by the interaction between cognition and emotion.
The self-learning algorithm updates a memory matrix W =, , w(a,s), , such that in each iteration executes the following machine learning routine:
# in situation ''s'' perform action ''a''
# receive consequence situation ''s
# compute emotion of being in consequence situation ''v(s')''
# update crossbar memory ''w'(a,s) = w(a,s) + v(s')''
It is a system with only one input, situation, and only one output, action (or behavior) a. There is neither a separate reinforcement input nor an advice input from the environment. The backpropagated value (secondary reinforcement) is the emotion toward the consequence situation. The CAA exists in two environments, one is the behavioral environment where it behaves, and the other is the genetic environment, wherefrom it initially and only once receives initial emotions about situations to be encountered in the behavioral environment. After receiving the genome (species) vector from the genetic environment, the CAA learns a goal-seeking behavior, in an environment that contains both desirable and undesirable situations.
Feature learning
Several learning algorithms aim at discovering better representations of the inputs provided during training.
Classic examples include
principal components analysis
Principal component analysis (PCA) is a popular technique for analyzing large datasets containing a high number of dimensions/features per observation, increasing the interpretability of data while preserving the maximum amount of information, and ...
and cluster analysis. Feature learning algorithms, also called representation learning algorithms, often attempt to preserve the information in their input but also transform it in a way that makes it useful, often as a pre-processing step before performing classification or predictions. This technique allows reconstruction of the inputs coming from the unknown data-generating distribution, while not being necessarily faithful to configurations that are implausible under that distribution. This replaces manual
feature engineering
Feature engineering or feature extraction or feature discovery is the process of using domain knowledge to extract features (characteristics, properties, attributes) from raw data. The motivation is to use these extra features to improve the qua ...
, and allows a machine to both learn the features and use them to perform a specific task.
Feature learning can be either supervised or unsupervised. In supervised feature learning, features are learned using labeled input data. Examples include
artificial neural network
Artificial neural networks (ANNs), usually simply called neural networks (NNs) or neural nets, are computing systems inspired by the biological neural networks that constitute animal brains.
An ANN is based on a collection of connected unit ...
s,
multilayer perceptron
A multilayer perceptron (MLP) is a fully connected class of feedforward artificial neural network (ANN). The term MLP is used ambiguously, sometimes loosely to mean ''any'' feedforward ANN, sometimes strictly to refer to networks composed of mul ...
s, and supervised
dictionary learning. In unsupervised feature learning, features are learned with unlabeled input data. Examples include dictionary learning,
independent component analysis
In signal processing, independent component analysis (ICA) is a computational method for separating a multivariate signal into additive subcomponents. This is done by assuming that at most one subcomponent is Gaussian and that the subcomponents ar ...
,
autoencoder
An autoencoder is a type of artificial neural network used to learn efficient codings of unlabeled data ( unsupervised learning). The encoding is validated and refined by attempting to regenerate the input from the encoding. The autoencoder lea ...
s,
matrix factorization
In the mathematical discipline of linear algebra, a matrix decomposition or matrix factorization is a factorization of a matrix into a product of matrices. There are many different matrix decompositions; each finds use among a particular class of ...
and various forms of
clustering.
Manifold learning
Nonlinear dimensionality reduction, also known as manifold learning, refers to various related techniques that aim to project high-dimensional data onto lower-dimensional latent manifolds, with the goal of either visualizing the data in the low- ...
algorithms attempt to do so under the constraint that the learned representation is low-dimensional.
Sparse coding
Neural coding (or Neural representation) is a neuroscience field concerned with characterising the hypothetical relationship between the stimulus and the individual or ensemble neuronal responses and the relationship among the electrical activit ...
algorithms attempt to do so under the constraint that the learned representation is sparse, meaning that the mathematical model has many zeros.
Multilinear subspace learning
Multilinear subspace learning is an approach to dimensionality reduction.M. A. O. Vasilescu, D. Terzopoulos (2003"Multilinear Subspace Analysis of Image Ensembles" "Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVP ...
algorithms aim to learn low-dimensional representations directly from
tensor
In mathematics, a tensor is an algebraic object that describes a multilinear relationship between sets of algebraic objects related to a vector space. Tensors may map between different objects such as vectors, scalars, and even other tensor ...
representations for multidimensional data, without reshaping them into higher-dimensional vectors.
Deep learning algorithms discover multiple levels of representation, or a hierarchy of features, with higher-level, more abstract features defined in terms of (or generating) lower-level features. It has been argued that an intelligent machine is one that learns a representation that disentangles the underlying factors of variation that explain the observed data.
Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process. However, real-world data such as images, video, and sensory data has not yielded attempts to algorithmically define specific features. An alternative is to discover such features or representations through examination, without relying on explicit algorithms.
Sparse dictionary learning
Sparse dictionary learning is a feature learning method where a training example is represented as a linear combination of
basis functions, and is assumed to be a
sparse matrix
In numerical analysis and scientific computing, a sparse matrix or sparse array is a matrix in which most of the elements are zero. There is no strict definition regarding the proportion of zero-value elements for a matrix to qualify as sparse b ...
. The method is
strongly NP-hard and difficult to solve approximately. A popular
heuristic
A heuristic (; ), or heuristic technique, is any approach to problem solving or self-discovery that employs a practical method that is not guaranteed to be optimal, perfect, or rational, but is nevertheless sufficient for reaching an immediate ...
method for sparse dictionary learning is the
K-SVD
In applied mathematics, K-SVD is a dictionary learning algorithm for creating a dictionary for sparse representations, via a singular value decomposition approach. K-SVD is a generalization of the k-means clustering method, and it works by itera ...
algorithm. Sparse dictionary learning has been applied in several contexts. In classification, the problem is to determine the class to which a previously unseen training example belongs. For a dictionary where each class has already been built, a new training example is associated with the class that is best sparsely represented by the corresponding dictionary. Sparse dictionary learning has also been applied in
image de-noising. The key idea is that a clean image patch can be sparsely represented by an image dictionary, but the noise cannot.
Anomaly detection
In
data mining, anomaly detection, also known as outlier detection, is the identification of rare items, events or observations which raise suspicions by differing significantly from the majority of the data.
Typically, the anomalous items represent an issue such as
bank fraud, a structural defect, medical problems or errors in a text. Anomalies are referred to as
outliers, novelties, noise, deviations and exceptions.
In particular, in the context of abuse and network intrusion detection, the interesting objects are often not rare objects, but unexpected bursts of inactivity. This pattern does not adhere to the common statistical definition of an outlier as a rare object. Many outlier detection methods (in particular, unsupervised algorithms) will fail on such data unless aggregated appropriately. Instead, a cluster analysis algorithm may be able to detect the micro-clusters formed by these patterns.
Three broad categories of anomaly detection techniques exist.
Unsupervised anomaly detection techniques detect anomalies in an unlabeled test data set under the assumption that the majority of the instances in the data set are normal, by looking for instances that seem to fit the least to the remainder of the data set. Supervised anomaly detection techniques require a data set that has been labeled as "normal" and "abnormal" and involves training a classifier (the key difference to many other statistical classification problems is the inherently unbalanced nature of outlier detection). Semi-supervised anomaly detection techniques construct a model representing normal behavior from a given normal training data set and then test the likelihood of a test instance to be generated by the model.
Robot learning
Robot learning Robot learning is a research field at the intersection of machine learning and robotics. It studies techniques allowing a robot to acquire novel skills or adapt to its environment through learning algorithms. The embodiment of the robot, situated in ...
is inspired by a multitude of machine learning methods, starting from supervised learning, reinforcement learning, and finally
meta-learning
Meta-learning is a branch of metacognition concerned with learning about one's own learning and learning processes.
The term comes from the meta prefix's modern meaning of an abstract recursion, or "X about X", similar to its use in metaknowled ...
(e.g. MAML).
Association rules
Association rule learning is a
rule-based machine learning method for discovering relationships between variables in large databases. It is intended to identify strong rules discovered in databases using some measure of "interestingness".
[Piatetsky-Shapiro, Gregory (1991), ''Discovery, analysis, and presentation of strong rules'', in Piatetsky-Shapiro, Gregory; and Frawley, William J.; eds., ''Knowledge Discovery in Databases'', AAAI/MIT Press, Cambridge, MA.]
Rule-based machine learning is a general term for any machine learning method that identifies, learns, or evolves "rules" to store, manipulate or apply knowledge. The defining characteristic of a rule-based machine learning algorithm is the identification and utilization of a set of relational rules that collectively represent the knowledge captured by the system. This is in contrast to other machine learning algorithms that commonly identify a singular model that can be universally applied to any instance in order to make a prediction. Rule-based machine learning approaches include
learning classifier systems, association rule learning, and
artificial immune systems.
Based on the concept of strong rules,
Rakesh Agrawal,
Tomasz Imieliński and Arun Swami introduced association rules for discovering regularities between products in large-scale transaction data recorded by
point-of-sale
The point of sale (POS) or point of purchase (POP) is the time and place at which a retail transaction is completed. At the point of sale, the merchant calculates the amount owed by the customer, indicates that amount, may prepare an invoic ...
(POS) systems in supermarkets.
For example, the rule
found in the sales data of a supermarket would indicate that if a customer buys onions and potatoes together, they are likely to also buy hamburger meat. Such information can be used as the basis for decisions about marketing activities such as promotional
pricing or
product placements. In addition to
market basket analysis
Affinity analysis falls under the umbrella term of data mining which uncovers meaningful correlations between different entities according to their co-occurrence in a data set. In almost all systems and processes, the application of affinity anal ...
, association rules are employed today in application areas including
Web usage mining,
intrusion detection
An intrusion detection system (IDS; also intrusion prevention system or IPS) is a device or software application that monitors a network or systems for malicious activity or policy violations. Any intrusion activity or violation is typically rep ...
,
continuous production
Continuous production is a flow production method used to manufacture, produce, or process materials without interruption. Continuous production is called a continuous process or a continuous flow process because the materials, either dry bulk ...
, and
bioinformatics. In contrast with
sequence mining
Sequential pattern mining is a topic of data mining concerned with finding statistically relevant patterns between data examples where the values are delivered in a sequence. It is usually presumed that the values are discrete, and thus time serie ...
, association rule learning typically does not consider the order of items either within a transaction or across transactions.
Learning classifier systems (LCS) are a family of rule-based machine learning algorithms that combine a discovery component, typically a
genetic algorithm, with a learning component, performing either
supervised learning
Supervised learning (SL) is a machine learning paradigm for problems where the available data consists of labelled examples, meaning that each data point contains features (covariates) and an associated label. The goal of supervised learning alg ...
,
reinforcement learning
Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine ...
, or
unsupervised learning
Unsupervised learning is a type of algorithm that learns patterns from untagged data. The hope is that through mimicry, which is an important mode of learning in people, the machine is forced to build a concise representation of its world and t ...
. They seek to identify a set of context-dependent rules that collectively store and apply knowledge in a
piecewise
In mathematics, a piecewise-defined function (also called a piecewise function, a hybrid function, or definition by cases) is a function defined by multiple sub-functions, where each sub-function applies to a different interval in the domain. P ...
manner in order to make predictions.
Inductive logic programming (ILP) is an approach to rule learning using
logic programming
Logic programming is a programming paradigm which is largely based on formal logic. Any program written in a logic programming language is a set of sentences in logical form, expressing facts and rules about some problem domain. Major logic pro ...
as a uniform representation for input examples, background knowledge, and hypotheses. Given an encoding of the known background knowledge and a set of examples represented as a logical database of facts, an ILP system will derive a hypothesized logic program that
entails all positive and no negative examples.
Inductive programming
Inductive programming (IP) is a special area of automatic programming, covering research from artificial intelligence and programming, which addresses learning of typically declarative (logic or functional) and often recursive programs from inc ...
is a related field that considers any kind of programming language for representing hypotheses (and not only logic programming), such as
functional programs.
Inductive logic programming is particularly useful in
bioinformatics and
natural language processing.
Gordon Plotkin
Gordon David Plotkin, (born 9 September 1946) is a theoretical computer scientist in the School of Informatics at the University of Edinburgh. Plotkin is probably best known for his introduction of structural operational semantics (SOS) and h ...
and
Ehud Shapiro laid the initial theoretical foundation for inductive machine learning in a logical setting. Shapiro built their first implementation (Model Inference System) in 1981: a Prolog program that inductively inferred logic programs from positive and negative examples. The term ''inductive'' here refers to
philosophical
Philosophy (from , ) is the systematized study of general and fundamental questions, such as those about existence, reason, knowledge, values, mind, and language. Such questions are often posed as problems to be studied or resolved. Some ...
induction, suggesting a theory to explain observed facts, rather than
mathematical induction
Mathematical induction is a method for proving that a statement ''P''(''n'') is true for every natural number ''n'', that is, that the infinitely many cases ''P''(0), ''P''(1), ''P''(2), ''P''(3), ... all hold. Informal metaphors help ...
, proving a property for all members of a well-ordered set.
Models
Performing machine learning involves creating a
model
A model is an informative representation of an object, person or system. The term originally denoted the plans of a building in late 16th-century English, and derived via French and Italian ultimately from Latin ''modulus'', a measure.
Models c ...
, which is trained on some training data and then can process additional data to make predictions. Various types of models have been used and researched for machine learning systems.
Artificial neural networks
![Colored neural network](https://upload.wikimedia.org/wikipedia/commons/4/46/Colored_neural_network.svg)
Artificial neural networks (ANNs), or
connectionist
Connectionism refers to both an approach in the field of cognitive science that hopes to explain mental phenomena using artificial neural networks (ANN) and to a wide range of techniques and algorithms using ANNs in the context of artificial int ...
systems, are computing systems vaguely inspired by the
biological neural networks that constitute animal
brain
A brain is an organ that serves as the center of the nervous system in all vertebrate and most invertebrate animals. It is located in the head, usually close to the sensory organs for senses such as vision. It is the most complex organ in a ve ...
s. Such systems "learn" to perform tasks by considering examples, generally without being programmed with any task-specific rules.
An ANN is a model based on a collection of connected units or nodes called "
artificial neuron
An artificial neuron is a mathematical function conceived as a model of biological neurons, a neural network. Artificial neurons are elementary units in an artificial neural network. The artificial neuron receives one or more inputs (representing ...
s", which loosely model the
neuron
A neuron, neurone, or nerve cell is an electrically excitable cell that communicates with other cells via specialized connections called synapses. The neuron is the main component of nervous tissue in all animals except sponges and placozoa. ...
s in a biological
brain
A brain is an organ that serves as the center of the nervous system in all vertebrate and most invertebrate animals. It is located in the head, usually close to the sensory organs for senses such as vision. It is the most complex organ in a ve ...
. Each connection, like the
synapses in a biological
brain
A brain is an organ that serves as the center of the nervous system in all vertebrate and most invertebrate animals. It is located in the head, usually close to the sensory organs for senses such as vision. It is the most complex organ in a ve ...
, can transmit information, a "signal", from one artificial neuron to another. An artificial neuron that receives a signal can process it and then signal additional artificial neurons connected to it. In common ANN implementations, the signal at a connection between artificial neurons is a
real number
In mathematics, a real number is a number that can be used to measure a ''continuous'' one-dimensional quantity such as a distance, duration or temperature. Here, ''continuous'' means that values can have arbitrarily small variations. Every ...
, and the output of each artificial neuron is computed by some non-linear function of the sum of its inputs. The connections between artificial neurons are called "edges". Artificial neurons and edges typically have a
weight
In science and engineering, the weight of an object is the force acting on the object due to gravity.
Some standard textbooks define weight as a vector quantity, the gravitational force acting on the object. Others define weight as a scalar qua ...
that adjusts as learning proceeds. The weight increases or decreases the strength of the signal at a connection. Artificial neurons may have a threshold such that the signal is only sent if the aggregate signal crosses that threshold. Typically, artificial neurons are aggregated into layers. Different layers may perform different kinds of transformations on their inputs. Signals travel from the first layer (the input layer) to the last layer (the output layer), possibly after traversing the layers multiple times.
The original goal of the ANN approach was to solve problems in the same way that a
human brain
The human brain is the central organ (anatomy), organ of the human nervous system, and with the spinal cord makes up the central nervous system. The brain consists of the cerebrum, the brainstem and the cerebellum. It controls most of the act ...
would. However, over time, attention moved to performing specific tasks, leading to deviations from
biology
Biology is the scientific study of life. It is a natural science with a broad scope but has several unifying themes that tie it together as a single, coherent field. For instance, all organisms are made up of cells that process hereditary i ...
. Artificial neural networks have been used on a variety of tasks, including
computer vision,
speech recognition
Speech recognition is an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enable the recognition and translation of spoken language into text by computers with the ...
,
machine translation
Machine translation, sometimes referred to by the abbreviation MT (not to be confused with computer-aided translation, machine-aided human translation or interactive translation), is a sub-field of computational linguistics that investigates t ...
,
social network
A social network is a social structure made up of a set of social actors (such as individuals or organizations), sets of dyadic ties, and other social interactions between actors. The social network perspective provides a set of methods for ...
filtering,
playing board and video games and
medical diagnosis
Medical diagnosis (abbreviated Dx, Dx, or Ds) is the process of determining which disease or condition explains a person's symptoms and signs. It is most often referred to as diagnosis with the medical context being implicit. The information r ...
.
Deep learning consists of multiple hidden layers in an artificial neural network. This approach tries to model the way the human brain processes light and sound into vision and hearing. Some successful applications of deep learning are
computer vision and
speech recognition
Speech recognition is an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enable the recognition and translation of spoken language into text by computers with the ...
.
Decision trees
![Decision Tree](https://upload.wikimedia.org/wikipedia/commons/e/eb/Decision_Tree.jpg)
Decision tree learning uses a
decision tree as a
predictive model
Predictive modelling uses statistics to predict outcomes. Most often the event one wants to predict is in the future, but predictive modelling can be applied to any type of unknown event, regardless of when it occurred. For example, predictive mod ...
to go from observations about an item (represented in the branches) to conclusions about the item's target value (represented in the leaves). It is one of the predictive modeling approaches used in statistics, data mining, and machine learning. Tree models where the target variable can take a discrete set of values are called classification trees; in these tree structures,
leaves represent class labels, and branches represent
conjunction
Conjunction may refer to:
* Conjunction (grammar), a part of speech
* Logical conjunction, a mathematical operator
** Conjunction introduction, a rule of inference of propositional logic
* Conjunction (astronomy), in which two astronomical bodies ...
s of features that lead to those class labels. Decision trees where the target variable can take continuous values (typically
real numbers) are called regression trees. In decision analysis, a decision tree can be used to visually and explicitly represent decisions and
decision making. In data mining, a decision tree describes data, but the resulting classification tree can be an input for decision-making.
Support-vector machines
Support-vector machines (SVMs), also known as support-vector networks, are a set of related
supervised learning
Supervised learning (SL) is a machine learning paradigm for problems where the available data consists of labelled examples, meaning that each data point contains features (covariates) and an associated label. The goal of supervised learning alg ...
methods used for classification and regression. Given a set of training examples, each marked as belonging to one of two categories, an SVM training algorithm builds a model that predicts whether a new example falls into one category.
An SVM training algorithm is a non-
probabilistic,
binary
Binary may refer to:
Science and technology Mathematics
* Binary number, a representation of numbers using only two digits (0 and 1)
* Binary function, a function that takes two arguments
* Binary operation, a mathematical operation that ta ...
,
linear classifier
In the field of machine learning, the goal of statistical classification is to use an object's characteristics to identify which class (or group) it belongs to. A linear classifier achieves this by making a classification decision based on the val ...
, although methods such as
Platt scaling
In machine learning, Platt scaling or Platt calibration is a way of transforming the outputs of a classification model into a probability distribution over classes. The method was invented by John Platt in the context of support vector machine ...
exist to use SVM in a probabilistic classification setting. In addition to performing linear classification, SVMs can efficiently perform a non-linear classification using what is called the
kernel trick
In machine learning, kernel machines are a class of algorithms for pattern analysis, whose best known member is the support-vector machine (SVM). The general task of pattern analysis is to find and study general types of relations (for example ...
, implicitly mapping their inputs into high-dimensional feature spaces.
Regression analysis
Regression analysis encompasses a large variety of statistical methods to estimate the relationship between input variables and their associated features. Its most common form is
linear regression, where a single line is drawn to best fit the given data according to a mathematical criterion such as
ordinary least squares
In statistics, ordinary least squares (OLS) is a type of linear least squares method for choosing the unknown parameters in a linear regression model (with fixed level-one effects of a linear function of a set of explanatory variables) by the ...
. The latter is often extended by
regularization
Regularization may refer to:
* Regularization (linguistics)
* Regularization (mathematics)
* Regularization (physics)
In physics, especially quantum field theory, regularization is a method of modifying observables which have singularities in ...
methods to mitigate overfitting and bias, as in
ridge regression
Ridge regression is a method of estimating the coefficients of multiple- regression models in scenarios where the independent variables are highly correlated. It has been used in many fields including econometrics, chemistry, and engineering. Als ...
. When dealing with non-linear problems, go-to models include
polynomial regression
In statistics, polynomial regression is a form of regression analysis in which the relationship between the independent variable ''x'' and the dependent variable ''y'' is modelled as an ''n''th degree polynomial in ''x''. Polynomial regression fi ...
(for example, used for trendline fitting in Microsoft Excel),
logistic regression
In statistics, the logistic model (or logit model) is a statistical model that models the probability of an event taking place by having the log-odds for the event be a linear combination of one or more independent variables. In regression a ...
(often used in
statistical classification
In statistics, classification is the problem of identifying which of a set of categories (sub-populations) an observation (or observations) belongs to. Examples are assigning a given email to the "spam" or "non-spam" class, and assigning a diagn ...
) or even
kernel regression
In statistics, kernel regression is a non-parametric technique to estimate the conditional expectation of a random variable. The objective is to find a non-linear relation between a pair of random variables ''X'' and ''Y''.
In any nonparametric ...
, which introduces non-linearity by taking advantage of the
kernel trick
In machine learning, kernel machines are a class of algorithms for pattern analysis, whose best known member is the support-vector machine (SVM). The general task of pattern analysis is to find and study general types of relations (for example ...
to implicitly map input variables to higher-dimensional space.
Bayesian networks
A Bayesian network, belief network, or directed acyclic graphical model is a probabilistic
graphical model
A graphical model or probabilistic graphical model (PGM) or structured probabilistic model is a probabilistic model for which a graph expresses the conditional dependence structure between random variables. They are commonly used in probabili ...
that represents a set of
random variables and their
conditional independence
In probability theory, conditional independence describes situations wherein an observation is irrelevant or redundant when evaluating the certainty of a hypothesis. Conditional independence is usually formulated in terms of conditional probabil ...
with a
directed acyclic graph
In mathematics, particularly graph theory, and computer science, a directed acyclic graph (DAG) is a directed graph with no directed cycles. That is, it consists of vertices and edges (also called ''arcs''), with each edge directed from one v ...
(DAG). For example, a Bayesian network could represent the probabilistic relationships between diseases and symptoms. Given symptoms, the network can be used to compute the probabilities of the presence of various diseases. Efficient algorithms exist that perform
inference and learning. Bayesian networks that model sequences of variables, like
speech signals or
protein sequences, are called
dynamic Bayesian network
A Dynamic Bayesian Network (DBN) is a Bayesian network (BN) which relates variables to each other over adjacent time steps. This is often called a ''Two-Timeslice'' BN (2TBN) because it says that at any point in time T, the value of a variable c ...
s. Generalizations of Bayesian networks that can represent and solve decision problems under uncertainty are called
influence diagrams.
Gaussian processes
A Gaussian process is a
stochastic process in which every finite collection of the random variables in the process has a
multivariate normal distribution
In probability theory and statistics, the multivariate normal distribution, multivariate Gaussian distribution, or joint normal distribution is a generalization of the one-dimensional ( univariate) normal distribution to higher dimensions. One ...
, and it relies on a pre-defined
covariance function In probability theory and statistics, the covariance function describes how much two random variables change together (their ''covariance'') with varying spatial or temporal separation. For a random field or stochastic process ''Z''(''x'') on a ...
, or kernel, that models how pairs of points relate to each other depending on their locations.
Given a set of observed points, or input–output examples, the distribution of the (unobserved) output of a new point as function of its input data, can be directly computed by looking as the observed points and the covariances between those points and the new, unobserved point.
Gaussian processes are popular surrogate models in
Bayesian optimization used to do
hyperparameter optimization In machine learning, hyperparameter optimization or tuning is the problem of choosing a set of optimal hyperparameters for a learning algorithm. A hyperparameter is a parameter whose value is used to control the learning process. By contrast, the va ...
.
Genetic algorithms
A genetic algorithm (GA) is a
search algorithm
In computer science, a search algorithm is an algorithm designed to solve a search problem. Search algorithms work to retrieve information stored within particular data structure, or calculated in the search space of a problem domain, with eith ...
and
heuristic
A heuristic (; ), or heuristic technique, is any approach to problem solving or self-discovery that employs a practical method that is not guaranteed to be optimal, perfect, or rational, but is nevertheless sufficient for reaching an immediate ...
technique that mimics the process of
natural selection
Natural selection is the differential survival and reproduction of individuals due to differences in phenotype. It is a key mechanism of evolution, the change in the heritable traits characteristic of a population over generations. Cha ...
, using methods such as
mutation
In biology, a mutation is an alteration in the nucleic acid sequence of the genome of an organism, virus, or extrachromosomal DNA. Viral genomes contain either DNA or RNA. Mutations result from errors during DNA replication, DNA or viral repl ...
and
crossover
Crossover may refer to:
Entertainment
Albums and songs
* ''Cross Over'' (Dan Peek album)
* ''Crossover'' (Dirty Rotten Imbeciles album), 1987
* ''Crossover'' (Intrigue album)
* ''Crossover'' (Hitomi Shimatani album)
* ''Crossover'' (Yoshino ...
to generate new
genotypes in the hope of finding good solutions to a given problem. In machine learning, genetic algorithms were used in the 1980s and 1990s. Conversely, machine learning techniques have been used to improve the performance of genetic and
evolutionary algorithm
In computational intelligence (CI), an evolutionary algorithm (EA) is a subset of evolutionary computation, a generic population-based metaheuristic optimization algorithm. An EA uses mechanisms inspired by biological evolution, such as reproduct ...
s.
Training models
Typically, machine learning models require a high quantity of reliable data in order for the models to perform accurate predictions. When training a machine learning model, machine learning engineers need to target and collect a large and representative sample of data. Data from the training set can be as varied as a corpus of text, a collection of images, sensor data, and data collected from individual users of a service.
Overfitting is something to watch out for when training a machine learning model. Trained models derived from biased or non-evaluated data can result in skewed or undesired predictions. Bias models may result in detrimental outcomes thereby furthering the negative impacts on society or objectives.
Algorithmic bias
Algorithmic bias describes systematic and repeatable errors in a computer system that create " unfair" outcomes, such as "privileging" one category over another in ways different from the intended function of the algorithm.
Bias can emerge from ...
is a potential result of data not being fully prepared for training. Machine learning ethics is becoming a field of study and notably be integrated within machine learning engineering teams.
Federated learning
Federated learning is an adapted form of
distributed artificial intelligence
Distributed Artificial Intelligence (DAI) also called Decentralized Artificial Intelligence is a subfield of artificial intelligence research dedicated to the development of distributed solutions for problems. DAI is closely related to and a pred ...
to training machine learning models that decentralizes the training process, allowing for users' privacy to be maintained by not needing to send their data to a centralized server. This also increases efficiency by decentralizing the training process to many devices. For example,
Gboard
Gboard is a virtual keyboard app developed by Google for Android and iOS devices. It was first released on iOS in May 2016, followed by a release on Android in December 2016, debuting as a major update to the already-established Google Keyboa ...
uses federated machine learning to train search query prediction models on users' mobile phones without having to send individual searches back to
Google
Google LLC () is an American Multinational corporation, multinational technology company focusing on Search Engine, search engine technology, online advertising, cloud computing, software, computer software, quantum computing, e-commerce, ar ...
.
Applications
There are many applications for machine learning, including:
*
Agriculture
Agriculture or farming is the practice of cultivating plants and livestock. Agriculture was the key development in the rise of sedentary human civilization, whereby farming of domesticated species created food surpluses that enabled people t ...
*
Anatomy
Anatomy () is the branch of biology concerned with the study of the structure of organisms and their parts. Anatomy is a branch of natural science that deals with the structural organization of living things. It is an old science, having it ...
*
Adaptive website An adaptive website is a website that builds a model of user activity and modifies the information and/or presentation of information to the user in order to better address the user's needs.
Overview
An adaptive website adjusts the structure, con ...
*
Affective computing
Affective computing is the study and development of systems and devices that can recognize, interpret, process, and simulate human affects. It is an interdisciplinary field spanning computer science, psychology, and cognitive science. While some ...
*
Astronomy
Astronomy () is a natural science that studies celestial objects and phenomena. It uses mathematics, physics, and chemistry in order to explain their origin and evolution. Objects of interest include planets, moons, stars, nebulae, g ...
*
Automated decision-making
Automated decision-making (ADM) involves the use of data, machines and algorithms to make decisions in a range of contexts, including public administration, business, health, education, law, employment, transport, media and entertainment, with var ...
*
Banking
A bank is a financial institution that accepts deposits from the public and creates a demand deposit while simultaneously making loans. Lending activities can be directly performed by the bank or indirectly through capital markets.
Becau ...
*
Behaviorism
*
Bioinformatics
*
Brain–machine interfaces
*
Cheminformatics
*
Citizen Science
*
Climate Science
Climatology (from Greek , ''klima'', "place, zone"; and , '' -logia'') or climate science is the scientific study of Earth's climate, typically defined as weather conditions averaged over a period of at least 30 years. This modern field of stu ...
*
Computer networks
A computer network is a set of computers sharing resources located on or provided by network nodes. The computers use common communication protocols over digital interconnections to communicate with each other. These interconnections are m ...
*
Computer vision
*
Credit-card fraud detection
*
Data quality
Data quality refers to the state of qualitative or quantitative pieces of information. There are many definitions of data quality, but data is generally considered high quality if it is "fit for tsintended uses in operations, decision making a ...
*
DNA sequence classification
*
Economics
Economics () is the social science that studies the production, distribution, and consumption of goods and services.
Economics focuses on the behaviour and interactions of economic agents and how economies work. Microeconomics analyzes ...
*
Financial market
A financial market is a market in which people trade financial securities and derivatives at low transaction costs. Some of the securities include stocks and bonds, raw materials and precious metals, which are known in the financial market ...
analysis
*
General game playing
General game playing (GGP) is the design of artificial intelligence programs to be able to play more than one game successfully. For many games like chess, computers are programmed to play these games using a specially designed algorithm, which ca ...
*
Handwriting recognition
Handwriting recognition (HWR), also known as handwritten text recognition (HTR), is the ability of a computer to receive and interpret intelligible handwritten input from sources such as paper documents, photographs, touch-screens and other de ...
*
Information retrieval
*
Insurance
Insurance is a means of protection from financial loss in which, in exchange for a fee, a party agrees to compensate another party in the event of a certain loss, damage, or injury. It is a form of risk management, primarily used to hedge ...
*
Internet fraud
Internet fraud is a type of cybercrime fraud or deception which makes use of the Internet and could involve hiding of information or providing incorrect information for the purpose of tricking victims out of money, property, and inheritance. Int ...
detection
*
Knowledge graph embedding
In representation learning, knowledge graph embedding (KGE), also referred to as knowledge representation learning (KRL), or multi-relation learning, is a machine learning task of learning a low-dimensional representation of a knowledge graph's en ...
*
Linguistics
Linguistics is the science, scientific study of human language. It is called a scientific study because it entails a comprehensive, systematic, objective, and precise analysis of all aspects of language, particularly its nature and structure ...
*
Machine learning control
*
Machine perception
Machine perception is the capability of a computer system to interpret data in a manner that is similar to the way humans use their senses to relate to the world around them. The basic method that the computers take in and respond to their enviro ...
*
Machine translation
Machine translation, sometimes referred to by the abbreviation MT (not to be confused with computer-aided translation, machine-aided human translation or interactive translation), is a sub-field of computational linguistics that investigates t ...
*
Marketing
Marketing is the process of exploring, creating, and delivering value to meet the needs of a target market in terms of goods and services; potentially including selection of a target audience; selection of certain attributes or themes to emph ...
*
Medical diagnosis
Medical diagnosis (abbreviated Dx, Dx, or Ds) is the process of determining which disease or condition explains a person's symptoms and signs. It is most often referred to as diagnosis with the medical context being implicit. The information r ...
*
Natural language processing
*
Natural language understanding
Natural-language understanding (NLU) or natural-language interpretation (NLI) is a subtopic of natural-language processing in artificial intelligence that deals with machine reading comprehension. Natural-language understanding is considered an A ...
*
Online advertising
Online advertising, also known as online marketing, Internet advertising, digital advertising or web advertising, is a form of marketing and advertising which uses the Internet to promote products and services to audiences and platform users. ...
*
Optimization
Mathematical optimization (alternatively spelled ''optimisation'') or mathematical programming is the selection of a best element, with regard to some criterion, from some set of available alternatives. It is generally divided into two subfi ...
*
Recommender system
A recommender system, or a recommendation system (sometimes replacing 'system' with a synonym such as platform or engine), is a subclass of information filtering system that provide suggestions for items that are most pertinent to a particular ...
s
*
Robot locomotion
Robot locomotion is the collective name for the various methods that robots use to transport themselves from place to place.
Wheeled robots are typically quite energy efficient and simple to control. However, other forms of locomotion may be more ...
*
Search engines
A search engine is a software system designed to carry out web searches. They search the World Wide Web in a systematic way for particular information specified in a textual web search query. The search results are generally presented in a ...
*
Sentiment analysis
Sentiment analysis (also known as opinion mining or emotion AI) is the use of natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjec ...
*
Sequence mining
Sequential pattern mining is a topic of data mining concerned with finding statistically relevant patterns between data examples where the values are delivered in a sequence. It is usually presumed that the values are discrete, and thus time serie ...
*
Software engineering
Software engineering is a systematic engineering approach to software development.
A software engineer is a person who applies the principles of software engineering to design, develop, maintain, test, and evaluate computer software. The term '' ...
*
Speech recognition
Speech recognition is an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enable the recognition and translation of spoken language into text by computers with the ...
*
Structural health monitoring
Structural health monitoring (SHM) involves the observation and analysis of a system over time using periodically sampled response measurements to monitor changes to the material and geometric properties of engineering structures such as bridges an ...
*
Syntactic pattern recognition
*
Telecommunication
Telecommunication is the transmission of information by various types of technologies over wire, radio, optical, or other electromagnetic systems. It has its origin in the desire of humans for communication over a distance greater than that fe ...
*
Theorem proving
Automated theorem proving (also known as ATP or automated deduction) is a subfield of automated reasoning and mathematical logic dealing with proving mathematical theorems by computer programs. Automated reasoning over mathematical proof was a maj ...
*
Time-series forecasting
*
User behavior analytics
User behavior analytics (UBA) is a cybersecurity process regarding the detection of insider threats, targeted attacks, and financial fraud that tracks a system's users. UBA looks at patterns of human behavior, and then analyzes observations to det ...
In 2006, the media-services provider
Netflix
Netflix, Inc. is an American subscription video on-demand over-the-top streaming service and production company based in Los Gatos, California. Founded in 1997 by Reed Hastings and Marc Randolph in Scotts Valley, California, it offers a fi ...
held the first "
Netflix Prize
The Netflix Prize was an open competition for the best collaborative filtering algorithm to predict user ratings for films, based on previous ratings without any other information about the users or films, i.e. without the users being identified ...
" competition to find a program to better predict user preferences and improve the accuracy of its existing Cinematch movie recommendation algorithm by at least 10%. A joint team made up of researchers from
AT&T Labs
AT&T Labs is the research & development division of AT&T, the telecommunications company. It employs some 1,800 people in various locations, including: Bedminster NJ; Middletown, NJ; Manhattan, NY; Warrenville, IL; Austin, TX; Dallas, TX; Atla ...
-Research in collaboration with the teams Big Chaos and Pragmatic Theory built an
ensemble model to win the Grand Prize in 2009 for $1 million. Shortly after the prize was awarded, Netflix realized that viewers' ratings were not the best indicators of their viewing patterns ("everything is a recommendation") and they changed their recommendation engine accordingly. In 2010 The Wall Street Journal wrote about the firm Rebellion Research and their use of machine learning to predict the financial crisis. In 2012, co-founder of
Sun Microsystems,
Vinod Khosla
Vinod Khosla (born 28 January 1955) is an Indian-American businessman and venture capitalist. He is a co-founder of Sun Microsystems and the founder of Khosla Ventures. Khosla made his wealth from early venture capital investments in areas suc ...
, predicted that 80% of medical doctors jobs would be lost in the next two decades to automated machine learning medical diagnostic software. In 2014, it was reported that a machine learning algorithm had been applied in the field of art history to study fine art paintings and that it may have revealed previously unrecognized influences among artists. In 2019
Springer Nature published the first research book created using machine learning. In 2020, machine learning technology was used to help make diagnoses and aid researchers in developing a cure for COVID-19. Machine learning is recently applied to predict the green behavior of human-being. Recently, machine learning technology is also applied to optimise smartphone's performance and thermal behaviour based on the user's interaction with the phone.
Limitations
Although machine learning has been transformative in some fields, machine-learning programs often fail to deliver expected results. Reasons for this are numerous: lack of (suitable) data, lack of access to the data, data bias, privacy problems, badly chosen tasks and algorithms, wrong tools and people, lack of resources, and evaluation problems.
In 2018, a self-driving car from
Uber
Uber Technologies, Inc. (Uber), based in San Francisco, provides mobility as a service, ride-hailing (allowing users to book a car and driver to transport them in a way similar to a taxi), food delivery (Uber Eats and Postmates), packa ...
failed to detect a pedestrian, who was killed after a collision. Attempts to use machine learning in healthcare with the
IBM Watson
IBM Watson is a question-answering computer system capable of answering questions posed in natural language, developed in IBM's DeepQA project by a research team led by principal investigator David Ferrucci. Watson was named after IBM's founder ...
system failed to deliver even after years of time and billions of dollars invested.
Machine learning has been used as a strategy to update the evidence related to a systematic review and increased reviewer burden related to the growth of biomedical literature. While it has improved with training sets, it has not yet developed sufficiently to reduce the workload burden without limiting the necessary sensitivity for the findings research themselves.
Bias
Machine learning approaches in particular can suffer from different data biases. A machine learning system trained specifically on current customers may not be able to predict the needs of new customer groups that are not represented in the training data. When trained on man-made data, machine learning is likely to pick up the constitutional and unconscious biases already present in society.
Language models learned from data have been shown to contain human-like biases. Machine learning systems used for criminal risk assessment have been found to be biased against black people. In 2015, Google photos would often tag black people as gorillas,
and in 2018 this still was not well resolved, but Google reportedly was still using the workaround to remove all gorillas from the training data, and thus was not able to recognize real gorillas at all. Similar issues with recognizing non-white people have been found in many other systems. In 2016, Microsoft tested a
chatbot
A chatbot or chatterbot is a software application used to conduct an on-line chat conversation via text or text-to-speech, in lieu of providing direct contact with a live human agent. Designed to convincingly simulate the way a human would behav ...
that learned from Twitter, and it quickly picked up racist and sexist language. Because of such challenges, the effective use of machine learning may take longer to be adopted in other domains. Concern for
fairness
Fairness or being fair can refer to:
* Justice
* The character in the award-nominated musical comedy '' A Theory of Justice: The Musical.''
* Equity (law), a legal principle allowing for the use of discretion and fairness when applying justice ...
in machine learning, that is, reducing bias in machine learning and propelling its use for human good is increasingly expressed by artificial intelligence scientists, including
Fei-Fei Li, who reminds engineers that "There's nothing artificial about AI...It's inspired by people, it's created by people, and—most importantly—it impacts people. It is a powerful tool we are only just beginning to understand, and that is a profound responsibility."
Explainability
Explainable AI (XAI), or Interpretable AI, or Explainable Machine Learning (XML), is artificial intelligence (AI) in which humans can understand the decisions or predictions made by the AI. It contrasts with the "black box" concept in machine learning where even its designers cannot explain why an AI arrived at a specific decision. By refining the mental models of users of AI-powered systems and dismantling their misconceptions, XAI promises to help users perform more effectively. XAI may be an implementation of the social right to explanation.
Overfitting
![Overfitted Data](https://upload.wikimedia.org/wikipedia/commons/6/68/Overfitted_Data.png)
Settling on a bad, overly complex theory gerrymandered to fit all the past training data is known as overfitting. Many systems attempt to reduce overfitting by rewarding a theory in accordance with how well it fits the data, but penalizing the theory in accordance with how complex the theory is.
Other limitations and vulnerabilities
Learners can also disappoint by "learning the wrong lesson". A toy example is that an image classifier trained only on pictures of brown horses and black cats might conclude that all brown patches are likely to be horses. A real-world example is that, unlike humans, current image classifiers often don't primarily make judgments from the spatial relationship between components of the picture, and they learn relationships between pixels that humans are oblivious to, but that still correlate with images of certain types of real objects. Modifying these patterns on a legitimate image can result in "adversarial" images that the system misclassifies.
Adversarial vulnerabilities can also result in nonlinear systems, or from non-pattern perturbations. Some systems are so brittle that changing a single adversarial pixel predictably induces misclassification. Machine learning models are often vulnerable to manipulation and/or evasion via
adversarial machine learning
Adversarial machine learning is the study of the attacks on machine learning algorithms, and of the defenses against such attacks. A recent survey exposes the fact that practitioners report a dire need for better protecting machine learning syste ...
.
Researchers have demonstrated how
backdoors can be placed undetectably into classifying (e.g. for categories "spam" and well-visible "not spam" of posts) machine learning models which are often developed and/or trained by third parties. Parties can change the classification of any input, including in cases for which a type of
data/software transparency is provided, possibly including
white-box access.
Model assessments
Classification of machine learning models can be validated by accuracy estimation techniques like the
holdout method, which splits the data in a training and test set (conventionally 2/3 training set and 1/3 test set designation) and evaluates the performance of the training model on the test set. In comparison, the K-fold-
cross-validation method randomly partitions the data into K subsets and then K experiments are performed each respectively considering 1 subset for evaluation and the remaining K-1 subsets for training the model. In addition to the holdout and cross-validation methods,
bootstrap, which samples n instances with replacement from the dataset, can be used to assess model accuracy.
In addition to overall accuracy, investigators frequently report
sensitivity and specificity
''Sensitivity'' and ''specificity'' mathematically describe the accuracy of a test which reports the presence or absence of a condition. Individuals for which the condition is satisfied are considered "positive" and those for which it is not are ...
meaning True Positive Rate (TPR) and True Negative Rate (TNR) respectively. Similarly, investigators sometimes report the
false positive rate
In statistics, when performing multiple comparisons, a false positive ratio (also known as fall-out or false alarm ratio) is the probability of falsely rejecting the null hypothesis for a particular test. The false positive rate is calculated as th ...
(FPR) as well as the
false negative rate (FNR). However, these rates are ratios that fail to reveal their numerators and denominators. The
total operating characteristic The total operating characteristic (TOC) is a statistical method to compare a Boolean variable versus a rank variable. TOC can measure the ability of an index variable to diagnose either presence or absence of a characteristic. The diagnosis of p ...
(TOC) is an effective method to express a model's diagnostic ability. TOC shows the numerators and denominators of the previously mentioned rates, thus TOC provides more information than the commonly used
receiver operating characteristic
A receiver operating characteristic curve, or ROC curve, is a graphical plot that illustrates the diagnostic ability of a binary classifier system as its discrimination threshold is varied. The method was originally developed for operators of m ...
(ROC) and ROC's associated area under the curve (AUC).
Ethics
Machine learning poses a host of
ethical questions. Systems that are trained on datasets collected with biases may exhibit these biases upon use (
algorithmic bias
Algorithmic bias describes systematic and repeatable errors in a computer system that create " unfair" outcomes, such as "privileging" one category over another in ways different from the intended function of the algorithm.
Bias can emerge from ...
), thus digitizing cultural prejudices. For example, in 1988, the UK's Commission for Racial Equality found that St. George's Medical School had been using a computer program trained from data of previous admissions staff and this program had denied nearly 60 candidates who were found to be either women or had non-European sounding names.
Using job hiring data from a firm with racist hiring policies may lead to a machine learning system duplicating the bias by scoring job applicants by similarity to previous successful applicants.
Responsible
collection of data and documentation of algorithmic rules used by a system thus is a critical part of machine learning.
AI can be well-equipped to make decisions in technical fields, which rely heavily on data and historical information. These decisions rely on the objectivity and logical reasoning. Because human languages contain biases, machines trained on language ''
corpora
Corpus is Latin for "body". It may refer to:
Linguistics
* Text corpus, in linguistics, a large and structured set of texts
* Speech corpus, in linguistics, a large set of speech audio files
* Corpus linguistics, a branch of linguistics
Music
* ...
'' will necessarily also learn these biases.
Other forms of ethical challenges, not related to personal biases, are seen in health care. There are concerns among health care professionals that these systems might not be designed in the public's interest but as income-generating machines. This is especially true in the United States where there is a long-standing ethical dilemma of improving health care, but also increase profits. For example, the algorithms could be designed to provide patients with unnecessary tests or medication in which the algorithm's proprietary owners hold stakes. There is potential for machine learning in health care to provide professionals an additional tool to diagnose, medicate, and plan recovery paths for patients, but this requires these biases to be mitigated.
Hardware
Since the 2010s, advances in both machine learning algorithms and computer hardware have led to more efficient methods for training
deep neural network
Deep learning (also known as deep structured learning) is part of a broader family of machine learning methods based on artificial neural networks with representation learning. Learning can be supervised, semi-supervised or unsupervised.
D ...
s (a particular narrow subdomain of machine learning) that contain many layers of non-linear hidden units. By 2019, graphic processing units (
GPU
A graphics processing unit (GPU) is a specialized electronic circuit designed to manipulate and alter memory to accelerate the creation of images in a frame buffer intended for output to a display device. GPUs are used in embedded systems, mobi ...
s), often with AI-specific enhancements, had displaced CPUs as the dominant method of training large-scale commercial cloud AI.
OpenAI
OpenAI is an artificial intelligence (AI) research laboratory consisting of the for-profit corporation OpenAI LP and its parent company, the non-profit OpenAI Inc. The company conducts research in the field of AI with the stated goal of promo ...
estimated the hardware computing used in the largest deep learning projects from AlexNet (2012) to AlphaZero (2017), and found a 300,000-fold increase in the amount of compute required, with a doubling-time trendline of 3.4 months.
Neuromorphic/Physical Neural Networks
A
physical neural network or
Neuromorphic computer is a type of
artificial neural network
Artificial neural networks (ANNs), usually simply called neural networks (NNs) or neural nets, are computing systems inspired by the biological neural networks that constitute animal brains.
An ANN is based on a collection of connected unit ...
in which an electrically adjustable material is used to emulate the function of a
neural synapse
In the nervous system, a synapse is a structure that permits a neuron (or nerve cell) to pass an electrical or chemical signal to another neuron or to the target effector cell.
Synapses are essential to the transmission of nervous impulses from ...
. "Physical" neural network is used to emphasize the reliance on physical hardware used to emulate
neurons as opposed to software-based approaches. More generally the term is applicable to other artificial neural networks in which a
memristor
A memristor (; a portmanteau of ''memory resistor'') is a non-linear two-terminal electrical component relating electric charge and magnetic flux linkage. It was described and named in 1971 by Leon Chua, completing a theoretical quartet of fu ...
or other electrically adjustable resistance material is used to emulate a neural synapse.
Embedded Machine Learning
Embedded Machine Learning is a sub-field of machine learning, where the machine learning model is run on
embedded systems
An embedded system is a computer system—a combination of a computer processor, computer memory, and input/output peripheral devices—that has a dedicated function within a larger mechanical or electronic system. It is ''embedded'' ...
with limited computing resources such as
wearable computer
A wearable computer, also known as a body-borne computer, is a computing device worn on the body. The definition of 'wearable computer' may be narrow or broad, extending to smartphones or even ordinary wristwatches.
Wearables may be for general ...
s,
edge device
An edge device is a device that provides an entry point into enterprise or service provider core networks. Examples include routers, routing switches, integrated access devices (IADs), multiplexers, and a variety of metropolitan area network (MA ...
s and
microcontrollers
A microcontroller (MCU for ''microcontroller unit'', often also MC, UC, or μC) is a small computer on a single VLSI integrated circuit (IC) chip. A microcontroller contains one or more CPUs ( processor cores) along with memory and programmabl ...
. Running machine learning model in embedded devices removes the need for transferring and storing data on cloud servers for further processing, henceforth, reducing data breaches and privacy leaks happening because of transferring data, and also minimizes theft of intellectual properties, personal data and business secrets. Embedded Machine Learning could be applied through several techniques including
hardware acceleration, using
approximate computing
Approximate computing is an emerging paradigm for energy-efficient and/or high-performance design. It includes a plethora of computation techniques that return a possibly inaccurate result rather than a guaranteed accurate result, and that can be u ...
, optimization of machine learning models and many more.
Software
Software suite
A software suite (also known as an application suite) is a collection of computer programs (application software, or programming software) of related functionality, sharing a similar user interface and the ability to easily exchange data with eac ...
s containing a variety of machine learning algorithms include the following:
Free and open-source software
*
Caffe
*
Deeplearning4j
Eclipse Deeplearning4j is a programming library written in Java for the Java virtual machine (JVM). It is a framework with wide support for deep learning algorithms. Deeplearning4j includes implementations of the restricted Boltzmann machine, d ...
*
DeepSpeed
DeepSpeed is an open source deep learning optimization library for PyTorch. The library is designed to reduce computing power and memory use and to train large distributed models with better parallelism on existing computer hardware. DeepSpeed i ...
*
ELKI
ELKI (for ''Environment for DeveLoping KDD-Applications Supported by Index-Structures'') is a data mining (KDD, knowledge discovery in databases) software framework developed for use in research and teaching. It was originally at the database ...
*
Google JAX
Google JAX is a machine learning framework for transforming numerical functions. It is described as bringing together a modified version oautograd(automatic obtaining of the gradient function through differentiation of a function) and TensorFlow'X ...
*
Infer.NET
Infer.NET is a free and open source .NET software library for machine learning. It supports running Bayesian inference in graphical models and can also be used for probabilistic programming.
Overview
Infer.NET follows a model-based approach an ...
*
Keras
Keras is an open-source software library that provides a Python interface for artificial neural networks. Keras acts as an interface for the TensorFlow library.
Up until version 2.3, Keras supported multiple backends, including TensorFlow, Mic ...
*
Kubeflow
*
LightGBM
LightGBM, short for light gradient-boosting machine, is a free and open-source distributed gradient-boosting framework for machine learning, originally developed by Microsoft. It is based on decision tree algorithms and used for ranking, class ...
*
Mahout
A mahout is an elephant rider, trainer, or keeper. Mahouts were used since antiquity for both civilian and military use. Traditionally, mahouts came from ethnic groups with generations of elephant keeping experience, with a mahout retaining h ...
*
Mallet
*
Microsoft Cognitive Toolkit
*
ML.NET
ML.NET is a free software machine learning library for the C# and F# programming languages. It also supports Python models when used together with NimbusML. The preview release of ML.NET included transforms for feature engineering like n-gram c ...
*
mlpack
mlpack is a machine learning software library for C++, built on top of the Armadillo library and thensmallennumerical optimization library. mlpack has an emphasis on scalability, speed, and ease-of-use. Its aim is to make machine learning possib ...
* MLFlow
*
MXNet
*
Neural Lab
*
OpenNN
*
Orange
Orange most often refers to:
*Orange (fruit), the fruit of the tree species '' Citrus'' × ''sinensis''
** Orange blossom, its fragrant flower
*Orange (colour), from the color of an orange, occurs between red and yellow in the visible spectrum
* ...
*
pandas (software)
pandas is a software library written for the Python programming language for data manipulation and analysis. In particular, it offers data structures and operations for manipulating numerical tables and time series. It is free software released ...
*
ROOT
In vascular plants, the roots are the organs of a plant that are modified to provide anchorage for the plant and take in water and nutrients into the plant body, which allows plants to grow taller and faster. They are most often below the su ...
(TMVA with ROOT)
*
scikit-learn
scikit-learn (formerly scikits.learn and also known as sklearn) is a free software machine learning library for the Python programming language.
It features various classification, regression and clustering algorithms including support-vector ...
*
Shogun
*
Spark MLlib
*
SystemML
*
TensorFlow
TensorFlow is a free and open-source software library for machine learning and artificial intelligence. It can be used across a range of tasks but has a particular focus on training and inference of deep neural networks. "It is machine learnin ...
*
Torch
A torch is a stick with combustible material at one end, which is ignited and used as a light source. Torches have been used throughout history, and are still used in processions, symbolic and religious events, and in juggling entertainment. I ...
/
PyTorch
PyTorch is a machine learning framework based on the Torch library, used for applications such as computer vision and natural language processing, originally developed by Meta AI and now part of the Linux Foundation umbrella. It is free and open ...
*
Weka
The weka, also known as the Māori hen or woodhen (''Gallirallus australis'') is a flightless bird species of the rail family. It is endemic to New Zealand. It is the only extant member of the genus '' Gallirallus''. Four subspecies are recogni ...
/
MOA
Moa are extinct giant flightless birds native to New Zealand.
The term has also come to be used for chicken in many Polynesian cultures and is found in the names of many chicken recipes, such as
Kale moa and Moa Samoa.
Moa or MOA may also refe ...
*
XGBoost
*
Yooreeka
Proprietary software with free and open-source editions
*
KNIME
KNIME (), the Konstanz Information Miner, is a free and open-source data analytics, reporting and integration platform. KNIME integrates various components for machine learning and data mining through its modular data pipelining "Building Blocks ...
*
RapidMiner
RapidMiner is a data science platform designed for enterprises that analyses the collective impact of organizations’ employees, expertise and data. Rapid Miner's data science platform is intended to support many analytics users across a broad A ...
Proprietary software
*
Amazon Machine Learning
Amazon Web Services, Inc. (AWS) is a subsidiary of Amazon that provides on-demand cloud computing platforms and APIs to individuals, companies, and governments, on a metered pay-as-you-go basis. These cloud computing web services provide di ...
*
Angoss KnowledgeSTUDIO
*
Azure Machine Learning
* Ayasdi
*
IBM Watson Studio
*
Google Cloud Vertex AI
*
Google Prediction API
*
IBM SPSS Modeler
*
KXEN Modeler
*
LIONsolver
LIONsolver is an integrated software for data mining, business intelligence, analytics, and modeling and reactive business intelligence approach. A non-profit version is also available as LIONoso.
LIONsolver is used to build models, visualize ...
*
Mathematica
*
MATLAB
MATLAB (an abbreviation of "MATrix LABoratory") is a proprietary multi-paradigm programming language and numeric computing environment developed by MathWorks. MATLAB allows matrix manipulations, plotting of functions and data, implementa ...
*
Neural Designer
*
NeuroSolutions
*
Oracle Data Mining
*
Oracle AI Platform Cloud Service
*
PolyAnalyst
PolyAnalyst is a data science software platform developed by Megaputer Intelligence that provides an environment for text mining, data mining, machine learning, and predictive analytics. It is used by Megaputer to build tools with applications ...
*
RCASE
*
SAS Enterprise Miner
*
SequenceL
*
Splunk
Splunk Inc. is an American software company based in San Francisco, California, that produces software for searching, monitoring, and analyzing machine-generated data via a Web-style interface.
Its software helps capture, index and correlate ...
*
STATISTICA Data Miner
Journals
*
Journal of Machine Learning Research
The ''Journal of Machine Learning Research'' is a peer-reviewed open access scientific journal covering machine learning. It was established in 2000 and the first editor-in-chief was Leslie Kaelbling. The current editors-in-chief are Francis Ba ...
*
Machine Learning
Machine learning (ML) is a field of inquiry devoted to understanding and building methods that 'learn', that is, methods that leverage data to improve performance on some set of tasks. It is seen as a part of artificial intelligence.
Machine ...
*
Nature Machine Intelligence
*
Neural Computation
Neural computation is the information processing performed by networks of neurons. Neural computation is affiliated with the philosophical tradition known as Computational theory of mind, also referred to as computationalism, which advances the th ...
* IEEE Transactions on Pattern Analysis and Machine Intelligence
Conferences
*
AAAI Conference on Artificial Intelligence
The AAAI Conference on Artificial Intelligence (AAAI) is one of the leading international academic conference in artificial intelligence held annually. Along with ICML, NeurIPS and ICLR, it is one of the primary conferences of high impact in mach ...
*
Association for Computational Linguistics (ACL)
*
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)
*
International Conference on Computational Intelligence Methods for Bioinformatics and Biostatistics (CIBB)
*
International Conference on Machine Learning (ICML)
*
International Conference on Learning Representations (ICLR)
*
International Conference on Intelligent Robots and Systems (IROS)
*
Conference on Knowledge Discovery and Data Mining (KDD)
*
Conference on Neural Information Processing Systems (NeurIPS)
See also
*
*
*
*
*
References
Sources
*
*
* .
*
Further reading
* Nils J. Nilsson,
Introduction to Machine Learning'.
*
Trevor Hastie
Trevor John Hastie (born 27 June 1953) is an American statistician and computer scientist. He is currently serving as the John A. Overdeck Professor of Mathematical Sciences and Professor of Statistics at Stanford University. Hastie is known for ...
,
Robert Tibshirani
Robert Tibshirani (born July 10, 1956) is a professor in the Departments of Statistics and Biomedical Data Science at Stanford University. He was a professor at the University of Toronto from 1985 to 1998. In his work, he develops statistical to ...
and
Jerome H. Friedman (2001).
The Elements of Statistical Learning', Springer. .
*
Pedro Domingos (September 2015), ''
The Master Algorithm'', Basic Books,
* Ian H. Witten and Eibe Frank (2011). ''Data Mining: Practical machine learning tools and techniques'' Morgan Kaufmann, 664pp., .
* Ethem Alpaydin (2004). ''Introduction to Machine Learning'', MIT Press, .
*
David J. C. MacKay
Professor Sir David John Cameron MacKay (22 April 1967 – 14 April 2016) was a British physicist, mathematician, and academic. He was the Regius Professor of Engineering in the Department of Engineering at the University of Cambridge and f ...
.
Information Theory, Inference, and Learning Algorithms' Cambridge: Cambridge University Press, 2003.
*
Richard O. Duda,
Peter E. Hart, David G. Stork (2001) ''Pattern classification'' (2nd edition), Wiley, New York, .
*
Christopher Bishop
Christopher Michael Bishop (born 7 April 1959) is the Laboratory Director at Microsoft Research Cambridge, Honorary Professor of Computer Science at the University of Edinburgh and a Fellow of Darwin College, Cambridge. Bishop is a member of ...
(1995). ''Neural Networks for Pattern Recognition'', Oxford University Press. .
* Stuart Russell & Peter Norvig, (2009).
Artificial Intelligence – A Modern Approach'. Pearson, .
*
Ray Solomonoff
Ray Solomonoff (July 25, 1926 – December 7, 2009) was the inventor of algorithmic probability, his General Theory of Inductive Inference (also known as Universal Inductive Inference),Samuel Rathmanner and Marcus Hutter. A philosophical treatise ...
, ''An Inductive Inference Machine'', IRE Convention Record, Section on Information Theory, Part 2, pp., 56–62, 1957.
*
Ray Solomonoff
Ray Solomonoff (July 25, 1926 – December 7, 2009) was the inventor of algorithmic probability, his General Theory of Inductive Inference (also known as Universal Inductive Inference),Samuel Rathmanner and Marcus Hutter. A philosophical treatise ...
,
An Inductive Inference Machine' A privately circulated report from the 1956
Dartmouth Summer Research Conference on AI.
* Kevin P. Murphy (2021).
Probabilistic Machine Learning: An Introduction', MIT Press.
External links
*
International Machine Learning Societymlossis an academic database of open-source machine learning software.
{{Authority control
Cybernetics
Learning