|
Error Tolerance (PAC Learning)
In PAC learning, error tolerance refers to the ability of an algorithm to learn when the examples received have been corrupted in some way. In fact, this is a very common and important issue since in many applications it is not possible to access noise-free data. Noise can interfere with the learning process at different levels: the algorithm may receive data that have been occasionally mislabeled, or the inputs may have some false information, or the classification of the examples may have been maliciously adulterated. Notation and the Valiant learning model In the following, let X be our n-dimensional input space. Let \mathcal be a class of functions that we wish to use in order to learn a \-valued target function f defined over X. Let \mathcal be the distribution of the inputs over X. The goal of a learning algorithm \mathcal is to choose the best function h \in \mathcal such that it minimizes error(h) = P_( h(x) \neq f(x)). Let us suppose we have a function size(f) that can me ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
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 ACM, 27, 1984. In this framework, the learner receives samples and must select a generalization function (called the ''hypothesis'') from a certain class of possible functions. The goal is that, with high probability (the "probably" part), the selected function will have low generalization error (the "approximately correct" part). The learner must be able to learn the concept given any arbitrary approximation ratio, probability of success, or distribution of the samples. The model was later extended to treat noise (misclassified samples). An important innovation of the PAC framework is the introduction of computational complexity theory concepts to machine learning. In particular, the learner is expected to find efficient functions (t ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Algorithm
In mathematics and computer science, an algorithm () is a finite sequence of Rigour#Mathematics, mathematically rigorous instructions, typically used to solve a class of specific Computational problem, problems or to perform a computation. Algorithms are used as specifications for performing calculations and data processing. More advanced algorithms can use Conditional (computer programming), conditionals to divert the code execution through various routes (referred to as automated decision-making) and deduce valid inferences (referred to as automated reasoning). In contrast, a Heuristic (computer science), heuristic is an approach to solving problems without well-defined correct or optimal results.David A. Grossman, Ophir Frieder, ''Information Retrieval: Algorithms and Heuristics'', 2nd edition, 2004, For example, although social media recommender systems are commonly called "algorithms", they actually rely on heuristics as there is no truly "correct" recommendation. As an e ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Leslie Valiant
Leslie Gabriel Valiant (born 28 March 1949) is a British American computer scientist and computational theorist. He was born to a chemical engineer father and a translator mother. He is currently the T. Jefferson Coolidge Professor of Computer Science and Applied Mathematics at Harvard University. Valiant was awarded the Turing Award in 2010, having been described by the Association for Computing Machinery, A.C.M. as a heroic figure in theoretical computer science and a role model for his courage and creativity in addressing some of the deepest unsolved problems in science; in particular for his "striking combination of depth and breadth". Education Valiant was educated at King's College, Cambridge, Imperial College London, and the University of Warwick where he received a PhD in computer science in 1974. Research and career Valiant is world-renowned for his work in Theoretical Computer Science. Among his many contributions to computational complexity theory, Complexity Theo ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Active Learning (machine Learning)
Active learning is a special case of machine learning in which a learning algorithm can interactively query a human user (or some other information source), to label new data points with the desired outputs. The human user must possess knowledge/expertise in the problem domain, including the ability to consult/research authoritative sources when necessary. In statistics literature, it is sometimes also called optimal experimental design. The information source is also called ''teacher'' or ''oracle''. There are situations in which unlabeled data is abundant but manual labeling is expensive. In such a scenario, learning algorithms can actively query the user/teacher for labels. This type of iterative supervised learning is called active learning. Since the learner chooses the examples, the number of examples to learn a concept can often be much lower than the number required in normal supervised learning. With this approach, there is a risk that the algorithm is overwhelmed by un ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Parity (mathematics)
In mathematics, parity is the Property (mathematics), property of an integer of whether it is even or odd. An integer is even if it is divisible by 2, and odd if it is not.. For example, −4, 0, and 82 are even numbers, while −3, 5, 23, and 69 are odd numbers. The above definition of parity applies only to integer numbers, hence it cannot be applied to numbers with decimals or fractions like 1/2 or 4.6978. See the section "Higher mathematics" below for some extensions of the notion of parity to a larger class of "numbers" or in other more general settings. Even and odd numbers have opposite parities, e.g., 22 (even number) and 13 (odd number) have opposite parities. In particular, the parity of zero is even. Any two consecutive integers have opposite parity. A number (i.e., integer) expressed in the decimal numeral system is even or odd according to whether its last digit is even or odd. That is, if the last digit is 1, 3, 5, 7, or 9, then it is odd; otherwise it is even—as ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Burst Error
In telecommunications, a burst error or error burst is a contiguous sequence of symbols, received over a communication channel, such that the first and last symbols are in error and there exists no contiguous subsequence of ''m'' correctly received symbols within the error burst. The integer parameter ''m'' is referred to as the ''guard band'' of the error burst. The last symbol in a burst and the first symbol in the following burst are accordingly separated by ''m'' correct symbols or more. The parameter ''m'' should be specified when describing an error burst. Channel model The Gilbert–Elliott model is a simple channel model introduced by Edgar Gilbert and E. O. Elliott that is widely used for describing burst error patterns in transmission channels and enables simulations of the digital error performance of communications links. It is based on a Markov chain In probability theory and statistics, a Markov chain or Markov process is a stochastic process describing a ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Sally Goldman
Sally Ann Goldman is an American computer scientist specializing in computational learning theory. She was a professor in the Department of Computer Science and Engineering at Washington University in St. Louis, and Edwin H. Murty Professor of Engineering, before leaving academia to join Google Research. She is also a successful amateur powerlifter. Education and career Goldman is originally from St. Louis, Missouri. She majored in computer science at Brown University, and then went to the Massachusetts Institute of Technology (MIT) for graduate study in computer science. She completed her Ph.D. there in 1990, with the dissertation ''Learning Binary Relations, Total Orders, and Read-Once Formulas'' supervised by Ron Rivest. As a faculty member at Washington University in St. Louis, she became Edwin H. Murty Professor of Engineering before leaving academia in 2008 to work for Google Research. Personal life Goldman was married to Kenneth J. Goldman, also a computer scientist fro ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Boolean Function
In mathematics, a Boolean function is a function whose arguments and result assume values from a two-element set (usually , or ). Alternative names are switching function, used especially in older computer science literature, and truth function (or logical function), used in logic. Boolean functions are the subject of Boolean algebra and switching theory. A Boolean function takes the form f:\^k \to \, where \ is known as the Boolean domain and k is a non-negative integer called the arity of the function. In the case where k=0, the function is a constant element of \. A Boolean function with multiple outputs, f:\^k \to \^m with m>1 is a vectorial or ''vector-valued'' Boolean function (an S-box in symmetric cryptography). There are 2^ different Boolean functions with k arguments; equal to the number of different truth tables with 2^k entries. Every k-ary Boolean function can be expressed as a propositional formula in k variables x_1,...,x_k, and two propositional formulas a ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Machine Learning
Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of Computational statistics, statistical algorithms that can learn from data and generalise to unseen data, and thus perform Task (computing), tasks without explicit Machine code, instructions. Within a subdiscipline in machine learning, advances in the field of deep learning have allowed Neural network (machine learning), neural networks, a class of statistical algorithms, to surpass many previous machine learning approaches in performance. ML finds application in many fields, including natural language processing, computer vision, speech recognition, email filtering, agriculture, and medicine. The application of ML to business problems is known as predictive analytics. Statistics and mathematical optimisation (mathematical programming) methods comprise the foundations of machine learning. Data mining is a related field of study, focusing on exploratory data analysi ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Data Mining
Data mining is the process of extracting and finding patterns in massive data sets involving methods at the intersection of machine learning, statistics, and database systems. Data mining is an interdisciplinary subfield of computer science and statistics with an overall goal of extracting information (with intelligent methods) from a data set and transforming the information into a comprehensible structure for further use. Data mining is the analysis step of the " knowledge discovery in databases" process, or KDD. Aside from the raw analysis step, it also involves database and data management aspects, data pre-processing, model and inference considerations, interestingness metrics, complexity considerations, post-processing of discovered structures, visualization, and online updating. The term "data mining" is a misnomer because the goal is the extraction of patterns and knowledge from large amounts of data, not the extraction (''mining'') of data itself. It also is a buzzwo ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Adversarial Machine Learning
Adversarial machine learning is the study of the attacks on machine learning algorithms, and of the defenses against such attacks. A survey from May 2020 revealed practitioners' common feeling for better protection of machine learning systems in industrial applications. Machine learning techniques are mostly designed to work on specific problem sets, under the assumption that the training and test data are generated from the same statistical distribution ( IID). However, this assumption is often dangerously violated in practical high-stake applications, where users may intentionally supply fabricated data that violates the statistical assumption. Most common attacks in adversarial machine learning include evasion attacks, data poisoning attacks, Byzantine attacks and model extraction. History At the MIT Spam Conference in January 2004, John Graham-Cumming showed that a machine-learning spam filter could be used to defeat another machine-learning spam filter by automatically ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Theoretical Computer Science
Theoretical computer science is a subfield of computer science and mathematics that focuses on the Abstraction, abstract and mathematical foundations of computation. It is difficult to circumscribe the theoretical areas precisely. The Association for Computing Machinery, ACM's Special Interest Group on Algorithms and Computation Theory (SIGACT) provides the following description: History While logical inference and mathematical proof had existed previously, in 1931 Kurt Gödel proved with his incompleteness theorem that there are fundamental limitations on what statements could be proved or disproved. Information theory was added to the field with A Mathematical Theory of Communication, a 1948 mathematical theory of communication by Claude Shannon. In the same decade, Donald Hebb introduced a mathematical model of Hebbian learning, learning in the brain. With mounting biological data supporting this hypothesis with some modification, the fields of neural networks and para ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
