|
Instrumental Convergence
Instrumental convergence is the hypothetical tendency for most sufficiently intelligent beings (both human and non-human) to pursue similar sub-goals, even if their ultimate goals are quite different. More precisely, agents (beings with agency) may pursue instrumental goals—goals which are made in pursuit of some particular end, but are not the end goals themselves—without end, provided that their ultimate (intrinsic) goals may never be fully satisfied. Instrumental convergence posits that an intelligent agent with unbounded but apparently harmless goals can act in surprisingly harmful ways. For example, a computer with the sole, unconstrained goal of solving an incredibly difficult mathematics problem like the Riemann hypothesis could attempt to turn the entire Earth into one giant computer in an effort to increase its computational power so that it can succeed in its calculations. Proposed basic AI drives include utility function or goal-content integrity, self-protection, ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Intelligent Agent
In artificial intelligence, an intelligent agent (IA) is anything which perceives its environment, takes actions autonomously in order to achieve goals, and may improve its performance with learning or may use knowledge. They may be simple or complex — a thermostat is considered an example of an intelligent agent, as is a human being, as is any system that meets the definition, such as a firm, a state, or a biome. Leading AI textbooks define "artificial intelligence" as the "study and design of intelligent agents", a definition that considers goal-directed behavior to be the essence of intelligence. Goal-directed agents are also described using a term borrowed from economics, "rational agent". An agent has an "objective function" that encapsulates all the IA's goals. Such an agent is designed to create and execute whatever plan will, upon completion, maximize the expected value of the objective function. For example, a reinforcement learning agent has a "reward function ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Reward Function
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 learning paradigms, alongside supervised learning and unsupervised learning. Reinforcement learning differs from supervised learning in not needing labelled input/output pairs to be presented, and in not needing sub-optimal actions to be explicitly corrected. Instead the focus is on finding a balance between exploration (of uncharted territory) and exploitation (of current knowledge). The environment is typically stated in the form of a Markov decision process (MDP), because many reinforcement learning algorithms for this context use dynamic programming techniques. The main difference between the classical dynamic programming methods and reinforcement learning algorithms is that the latter do not assume knowledge of an exact mathematica ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Gödel Machine
A Gödel machine is a hypothetical self-improving computer program that solves problems in an optimal way. It uses a recursive self-improvement protocol in which it rewrites its own code when it can prove the new code provides a better strategy. The machine was invented by Jürgen Schmidhuber (first proposed in 2003), but is named after Kurt Gödel who inspired the mathematical theories. The Gödel machine is often discussed when dealing with issues of meta-learning, also known as "learning to learn." Applications include automating human design decisions and transfer of knowledge between multiple related tasks, and may lead to design of more robust and general learning architectures. Though theoretically possible, no full implementation has been created. The Gödel machine is often compared with Marcus Hutter's AIXI, another formal specification for an artificial general intelligence. Schmidhuber points out that the Gödel machine could start out by implementing AIXItl as its init ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Jürgen Schmidhuber
Jürgen Schmidhuber (born 17 January 1963) is a German computer scientist most noted for his work in the field of artificial intelligence, deep learning and artificial neural networks. He is a co-director of the Dalle Molle Institute for Artificial Intelligence Research in Lugano, in Ticino in southern Switzerland. Following Google Scholar, from 2016 to 2021 he has received more than 100,000 scientific citations. He has been referred to as "father of modern AI," "father of AI," "dad of mature AI," "Papa" of famous AI products, "Godfather," and "father of deep learning." (Schmidhuber himself, however, has called Alexey Grigorevich Ivakhnenko the "father of deep learning.") Schmidhuber completed his undergraduate (1987) and PhD (1991) studies at the Technical University of Munich in Munich, Germany. His PhD advisors were Wilfried Brauer and Klaus Schulten. He taught there from 2004 until 2009 when he became a professor of artificial intelligence at the Università della Sviz ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Machine Intelligence Research Institute
The Machine Intelligence Research Institute (MIRI), formerly the Singularity Institute for Artificial Intelligence (SIAI), is a non-profit research institute focused since 2005 on identifying and managing potential existential risks from artificial general intelligence. MIRI's work has focused on a friendly AI approach to system design and on predicting the rate of technology development. History In 2000, Eliezer Yudkowsky founded the Singularity Institute for Artificial Intelligence with funding from Brian and Sabine Atkins, with the purpose of accelerating the development of artificial intelligence (AI). However, Yudkowsky began to be concerned that AI systems developed in the future could become superintelligent and pose risks to humanity, and in 2005 the institute moved to Silicon Valley and began to focus on ways to identify and manage those risks, which were at the time largely ignored by scientists in the field. Starting in 2006, the Institute organized the Singularity ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Drive Theory
In psychology, a drive theory, theory of drives or drive doctrine is a theory that attempts to analyze, classify or define the psychological drives. A drive is an instinctual need that has the power of driving the behavior of an individual; an "excitatory state produced by a homeostatic disturbance". Drive theory is based on the principle that organisms are born with certain psychological needs and that a negative state of tension is created when these needs are not satisfied. When a need is satisfied, drive is reduced and the organism returns to a state of homeostasis and relaxation. According to the theory, drive tends to increase over time and operates on a feedback control system, much like a thermostat. In 1943 two psychologists, Clark Hull and Kenneth Spence, had the first interest in this idea of motivation. They knew it was a sense of their motivation, drives, and an explanation of all behavior. After years of research, they created the drive theory. In a study conducted ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Self-preservation
Self-preservation is a behavior or set of behaviors that ensures the survival Survival, or the act of surviving, is the propensity of something to continue existing, particularly when this is done despite conditions that might kill or destroy it. The concept can be applied to humans and other living things (or, hypotheti ... of an organism. It is thought to be universal among all living organisms. For sentient organisms, pain and fear are integral parts of this mechanism. Pain motivates the individual to withdraw from damaging situations, to protect a damaged body part while it heals, and to avoid similar experiences in the future. Most pain resolves promptly once the painful stimulus is removed and the body has healed, but sometimes pain persists despite removal of the stimulus and apparent healing of the body; and sometimes pain arises in the absence of any detectable stimulus, damage or disease. Fear causes the organism to seek safety and may cause a release of adrenaline, wh ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Steve Omohundro
Stephen Malvern Omohundro (born 1959) is an American computer scientist whose areas of research include Hamiltonian physics, dynamical systems, programming languages, machine learning, machine vision, and the social implications of artificial intelligence. His current work uses rational economics to develop safe and beneficial intelligent technologies for better collaborative modeling, understanding, innovation, and decision making. Education Omohundro has degrees in physics and mathematics from Stanford University (Phi Beta Kappa) and a Ph.D. in physics from the University of California, Berkeley. Learning algorithms Omohundro started the "Vision and Learning Group" at the University of Illinois which produced 4 Masters and 2 Ph.D. theses. His work in learning algorithms included a number of efficient geometric algorithms, the manifold learning task and various algorithms for accomplishing this task, other related visual learning and modelling tasks, the model merging approach ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Identity Function
Graph of the identity function on the real numbers In mathematics, an identity function, also called an identity relation, identity map or identity transformation, is a function that always returns the value that was used as its argument, unchanged. That is, when is the identity function, the equality is true for all values of to which can be applied. Definition Formally, if is a set, the identity function on is defined to be a function with as its domain and codomain, satisfying In other words, the function value in the codomain is always the same as the input element in the domain . The identity function on is clearly an injective function as well as a surjective function, so it is bijective. The identity function on is often denoted by . In set theory, where a function is defined as a particular kind of binary relation, the identity function is given by the identity relation, or ''diagonal'' of . Algebraic properties If is any function, then we have ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Journal Of Artificial Intelligence Research
The ''Journal of Artificial Intelligence Research'' (''JAIR'') is an open access peer-reviewed scientific journal covering research in all areas of artificial intelligence. History It was established in 1993 as one of the first scientific journals distributed online. Paper volumes are printed by the AAAI Press. The Journal for Artificial Intelligence Research (JAIR) is one of the premier publication venues in artificial intelligence. JAIR also stands out in that, since its launch in 1993, it has been 100% open-access and non-profit. Content The Journal of Artificial Intelligence Research (JAIR) is dedicated to the rapid dissemination of important research results to the global artificial intelligence (AI) community. The journal’s scope encompasses all areas of AI, including agents and multi-agent systems, automated reasoning, constraint processing and search, knowledge representation, machine learning, natural language, planning and scheduling, robotics and vision, and unc ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Expected Value
In probability theory, the expected value (also called expectation, expectancy, mathematical expectation, mean, average, or first moment) is a generalization of the weighted average. Informally, the expected value is the arithmetic mean of a large number of independently selected outcomes of a random variable. The expected value of a random variable with a finite number of outcomes is a weighted average of all possible outcomes. In the case of a continuum of possible outcomes, the expectation is defined by integration. In the axiomatic foundation for probability provided by measure theory, the expectation is given by Lebesgue integration. The expected value of a random variable is often denoted by , , or , with also often stylized as or \mathbb. History The idea of the expected value originated in the middle of the 17th century from the study of the so-called problem of points, which seeks to divide the stakes ''in a fair way'' between two players, who have to end th ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
Expected Utility
The expected utility hypothesis is a popular concept in economics that serves as a reference guide for decisions when the payoff is uncertain. The theory recommends which option rational individuals should choose in a complex situation, based on their risk appetite and preferences. The expected utility hypothesis states an agent chooses between risky prospects by comparing expected utility values (i.e. the weighted sum of adding the respective utility values of payoffs multiplied by their probabilities). The summarised formula for expected utility is U(p)=\sum u(x_k)p_k where p_k is the probability that outcome indexed by k with payoff x_k is realized, and function ''u'' expresses the utility of each respective payoff. On a graph, the curvature of u will explain the agent's risk attitude. For example, if an agent derives 0 utils from 0 apples, 2 utils from one apple, and 3 utils from two apples, their expected utility for a 50–50 gamble between zero apples and two is 0.5''u''(0 ... [...More Info...] [...Related Items...] OR: [Wikipedia] [Google] [Baidu] |
.jpg "Click for more on -> Machine Intelligence Research Institute")
