Artificial intelligence

From Wikipedia, the free encyclopedia

"AI" redirects here. For other uses, see AI (disambiguation).
Garry Kasparov playing against Deep Blue, the first machine to win a chess match against a reigning world champion.
Garry Kasparov playing against Deep Blue, the first machine to win a chess match against a reigning world champion.

Artificial intelligence (AI) is both the intelligence of machines and the branch of computer science which aims to create it.

Major AI textbooks define artificial intelligence as "the study and design of intelligent agents,"[1] where an intelligent agent is a system that perceives its environment and takes actions which maximize its chances of success.[2] AI can be seen as a realization of an abstract intelligent agent (AIA) which exhibits the functional essence of intelligence.[3] John McCarthy, who coined the term in 1956,[4] defines it as "the science and engineering of making intelligent machines."[5]

Among the traits that researchers hope machines will exhibit are reasoning, knowledge, planning, learning, communication, perception and the ability to move and manipulate objects.[6] General intelligence (or "strong AI") has not yet been achieved and is a long-term goal of AI research.[7]

AI research uses tools and insights from many fields, including computer science, psychology, philosophy, neuroscience, cognitive science, linguistics, ontology, operations research, economics, control theory, probability, optimization and logic.[8] AI research also overlaps with tasks such as robotics, control systems, scheduling, data mining, logistics, speech recognition, facial recognition and many others.[9] Other names for the field have been proposed, such as computational intelligence,[10] synthetic intelligence,[10] intelligent systems,[11] or computational rationality.[12]

Artificial intelligence Portal

Contents

[edit] Perspectives on AI

[edit] AI in myth, fiction and speculation

Main articles: artificial intelligence in fiction, ethics of artificial intelligence, transhumanism, and Technological singularity

Humanity has imagined in great detail the implications of thinking machines or artificial beings. They appear in Greek myths, such as Talos of Crete, the golden robots of Hephaestus and Pygmalion's Galatea.[13] The earliest known humanoid robots (or automatons) were sacred statues worshipped in Egypt and Greece, believed to have been endowed with genuine consciousness by craftsman.[14] In medieval times, alchemists such as Paracelsus claimed to have created artificial beings.[15] Realistic clockwork imitations of human beings have been built by people such as Yan Shi,[16] Hero of Alexandria,[17] Al-Jazari[18] and Wolfgang von Kempelen.[19] Pamela McCorduck observes that "artificial intelligence in one form or another is an idea that has pervaded Western intellectual history, a dream in urgent need of being realized."[20]

In modern fiction, beginning with Mary Shelley's classic Frankenstein, writers have explored the ethical issues presented by thinking machines.[21] If a machine can be created that has intelligence, can it also feel? If it can feel, does it have the same rights as a human being? This is a key issue in Frankenstein as well as in modern science fiction: for example, the film Artificial Intelligence: A.I. considers a machine in the form of a small boy which has been given the ability to feel human emotions, including, tragically, the capacity to suffer. This issue is also being considered by futurists, such as California's Institute for the Future under the name "robot rights",[22] although many critics believe that the discussion is premature.[23][24]

Science fiction writers and futurists have also speculated on the technology's potential impact on humanity. In fiction, AI has appeared as a servant (R2D2), a comrade (Lt. Commander Data), an extension to human abilities (Ghost in the Shell), a conqueror (The Matrix), a dictator (With Folded Hands) and an exterminator (Terminator, Battlestar Galactica). Some realistic potential consequences of AI are decreased human labor demand,[25] the enhancement of human ability or experience,[26] and a need for redefinition of human identity and basic values.[27]

Futurists estimate the capabilities of machines using Moore's Law, which measures the relentless exponential improvement in digital technology with uncanny accuracy. Ray Kurzweil has calculated that desktop computers will have the same processing power as human brains by the year 2029, and that by 2045 artificial intelligence will reach a point where it is able to improve itself at a rate that far exceeds anything conceivable in the past, a scenario that science fiction writer Vernor Vinge named the "technological singularity".[28]

"Artificial intelligence is the next stage in evolution," Edward Fredkin said in the 1980s,[29] expressing an idea first proposed by Samuel Butler's Darwin Among the Machines (1863), and expanded upon by George Dyson in his book of the same name (1998). Several futurists and science fiction writers have predicted that human beings and machines will merge in the future into cyborgs that are more capable and powerful than either. This idea, called transhumanism, has roots in Aldous Huxley and Robert Ettinger, is now associated with robot designer Hans Moravec, cyberneticist Kevin Warwick and Ray Kurzweil.[28] Transhumanism has been illustrated in fiction as well, for example on the manga Ghost in the Shell

[edit] History of AI research

Main articles: history of artificial intelligence and timeline of artificial intelligence

In the middle of the 20th century, a handful of scientists began a new approach to building intelligent machines, based on recent discoveries in neurology, a new mathematical theory of information, an understanding of control and stability called cybernetics, and above all, by the invention of the digital computer, a machine based on the abstract essence of mathematical reasoning.[30]

The field of modern AI research was founded at conference on the campus of Dartmouth College in the summer of 1956.[31] Those who attended would become the leaders of AI research for many decades, especially John McCarthy, Marvin Minsky, Allen Newell and Herbert Simon, who founded AI laboratories at MIT, CMU and Stanford. They and their students wrote programs that were, to most people, simply astonishing:[32] computers were solving word problems in algebra, proving logical theorems and speaking English.[33] By the middle 60s their research was heavily funded by the U.S. Department of Defense[34] and they were optimistic about the future of the new field:

  • 1965, H. A. Simon: "[M]achines will be capable, within twenty years, of doing any work a man can do"[35]
  • 1967, Marvin Minsky: "Within a generation ... the problem of creating 'artificial intelligence' will substantially be solved."[36]

These predictions, and many like them, would not come true. They had failed to recognize the difficulty of some of the problems they faced.[37] In 1974, in response to the criticism of England's Sir James Lighthill and ongoing pressure from Congress to fund more productive projects, the U.S. and British governments cut off all undirected, exploratory research in AI. This was the first AI Winter.[38]

In the early 80s, AI research was revived by the commercial success of expert systems (a form of AI program that simulated the knowledge and analytical skills of one or more human experts) and by 1985 the market for AI had reached more than a billion dollars.[39] Minsky and others warned the community that enthusiasm for AI had spiraled out of control and that disappointment was sure to follow.[40] Beginning with the collapse of the Lisp Machine market in 1987, AI once again fell into disrepute, and a second, more lasting AI Winter began.[41]

In the 90s and early 21st century AI achieved its greatest successes, albeit somewhat behind the scenes. Artificial intelligence was adopted throughout the technology industry, providing the heavy lifting for logistics, data mining, medical diagnosis and many other areas.[42] The success was due to several factors: the incredible power of computers today (see Moore's law), a greater emphasis on solving specific subproblems, the creation of new ties between AI and other fields working on similar problems, and above all a new commitment by researchers to solid mathematical methods and rigorous scientific standards.[43]

[edit] Philosophy of AI

Mind and Brain Portal
Main article: philosophy of artificial intelligence
Can the brain be simulated by a digital computer? If it can, then would the simulation have a mind in the same sense that people do?
Can the brain be simulated by a digital computer? If it can, then would the simulation have a mind in the same sense that people do?

In a classic 1950 paper, Alan Turing posed the question "Can Machines Think?" In the years since, the philosophy of artificial intelligence has attempted to answer it.[44]

[edit] AI research

[edit] Problems of AI

While there is no universally accepted definition of intelligence,[52] AI researchers have studied several traits that are considered essential.[6]

[edit] Deduction, reasoning, problem solving

Early AI researchers developed algorithms that imitated the process of conscious, step-by-step reasoning that human beings use when they solve puzzles, play board games, or make logical deductions.[53] By the late 80s and 90s, AI research had also developed highly successful methods for dealing with uncertain or incomplete information, employing concepts from probability and economics.[54]

For difficult problems, most of these algorithms can require enormous computational resources — most experience a "combinatorial explosion": the amount of memory or computer time required becomes astronomical when the problem goes beyond a certain size. The search for more efficient problem solving algorithms is a high priority for AI research.[55]

It is not clear, however, that conscious human reasoning is any more efficient when faced with a difficult abstract problem. Cognitive scientists have demonstrated that human beings solve most of their problems using unconscious reasoning, rather than the conscious, step-by-step deduction that early AI research was able to model.[56] Embodied cognitive science argues that unconscious sensorimotor skills are essential to our problem solving abilities. It is hoped that sub-symbolic methods, like computational intelligence and situated AI, will be able to model these instinctive skills. The problem of unconscious problem solving, which forms part of our commonsense reasoning, is largely unsolved[dubious – discuss].

[edit] Knowledge representation

Main articles: knowledge representation and commonsense knowledge

Knowledge representation[57] and knowledge engineering[58] are central to AI research. Many of the problems machines are expected to solve will require extensive knowledge about the world. Among the things that AI needs to represent are: objects, properties, categories and relations between objects;[59] situations, events, states and time;[60] causes and effects;[61] knowledge about knowledge (what we know about what other people know);[62] and many other, less well researched domains. A complete representation of "what exists" is an ontology[63] (borrowing a word from traditional philosophy), of which the most general are called upper ontologies.

Among the most difficult problems in knowledge representation are:

  • Default reasoning and the qualification problem: Many of the things people know take the form of "working assumptions." For example, if a bird comes up in conversation, people typically picture an animal that is fist sized, sings, and flies. None of these things are true about birds in general. John McCarthy identified this problem in 1969[64] as the qualification problem: for any commonsense rule that AI researchers care to represent, there tend to be a huge number of exceptions. Almost nothing is simply true or false in the way that abstract logic requires. AI research has explored a number of solutions to this problem.[65]
  • Unconscious knowledge: Much of what people know isn't represented as "facts" or "statements" that they could actually say out loud. They take the form of intuitions or tendencies and are represented in the brain unconsciously and sub-symbolically. This unconscious knowledge informs, supports and provides a context for our conscious knowledge. As with the related problem of unconscious reasoning, it is hoped that situated AI or computational intelligence will provide ways to represent this kind of knowledge.
  • The breadth of common sense knowledge: The number of atomic facts that the average person knows is astronomical. Research projects that attempt to build a complete knowledge base of commonsense knowledge, such as Cyc, require enormous amounts of tedious step-by-step ontological engineering — they must be built, by hand, one complicated concept at a time.[66]

[edit] Planning

Main article: automated planning and scheduling

Intelligent agents must be able to set goals and achieve them.[67] They need a way to visualize the future: they must have a representation of the state of the world and be able to make predictions about how their actions will change it. They must also attempt to determine the utility or "value" of the choices available to it.[68]

In some planning problems, the agent can assume that it is the only thing acting on the world and it can be certain what the consequences of its actions may be.[69] However, if this is not true, it must periodically check if the world matches its predictions and it must change its plan as this becomes necessary, requiring the agent to reason under uncertainty.[70]

Multi-agent planning tries to determine the best plan for a community of agents, using cooperation and competition to achieve a given goal. Emergent behavior such as this is used by both evolutionary algorithms and swarm intelligence.[71]

[edit] Learning

Main article: machine learning

Important machine learning[72] problems are:

  • Unsupervised learning: find a model that matches a stream of input "experiences", and be able to predict what new "experiences" to expect.
  • Supervised learning, such as classification (be able to determine what category something belongs in, after seeing a number of examples of things from each category), or regression (given a set of numerical input/output examples, discover a continuous function that would generate the outputs from the inputs).
  • Reinforcement learning:[73] the agent is rewarded for good responses and punished for bad ones. (These can be analyzed in terms decision theory, using concepts like utility).

[edit] Natural language processing

Main article: natural language processing

Natural language processing[74] gives machines the ability to read and understand the languages human beings speak. Many researchers hope that a sufficiently powerful natural language processing system would be able to acquire knowledge on its own, by reading the existing text available over the internet. Some straightforward applications of natural language processing include information retrieval (or text mining) and machine translation.[75]

[edit] Motion and manipulation

ASIMO uses sensors and intelligent algorithms to avoid obstacles and navigate stairs.
ASIMO uses sensors and intelligent algorithms to avoid obstacles and navigate stairs.
Main article: robotics

The field of robotics[76] is closely related to AI. Intelligence is required for robots to be able to handle such tasks as object manipulation[77] and navigation, with sub-problems of localization (knowing where you are), mapping (learning what is around you) and motion planning (figuring out how to get there).[78]

[edit] Perception

Main articles: machine perception, computer vision, and speech recognition

Machine perception[79] is the ability to use input from sensors (such as cameras, microphones, sonar and others more exotic) to deduce aspects of the world. Computer vision[80] is the ability to analyze visual input. A few selected subproblems are speech recognition,[81] facial recognition and object recognition.[82]

[edit] Social intelligence

Main article: affective computing
Kismet, a robot with rudimentary social skills.
Kismet, a robot with rudimentary social skills.

Emotion and social skills play two roles for an intelligent agent:[83]

  • It must be able to predict the actions of others, by understanding their motives and emotional states. (This involves elements of game theory, decision theory, as well as the ability to model human emotions and the perceptual skills to detect emotions.)
  • For good human-computer interaction, an intelligent machine also needs to display emotions — at the very least it must appear polite and sensitive to the humans it interacts with. At best, it should appear to have normal emotions itself.

[edit] Creativity

Main article: Computational creativity

A sub-field of AI addresses creativity both theoretically (from a philosophical and psychological perspective) and practically (via specific implementations of systems that generate outputs that can be considered creative).

[edit] General intelligence

Main articles: strong AI and AI-complete

Most researchers hope that their work will eventually be incorporated into a machine with general intelligence (known as strong AI), combining all the skills above and exceeding human abilities at most or all of them.[7] A few believe that anthropomorphic features like artificial consciousness or an artificial brain may be required for such a project.

Many of the problems above are considered AI-complete: to solve one problem, you must solve them all. For example, even a straightforward, specific task like machine translation requires that the machine follow the author's argument (reason), know what it's talking about (knowledge), and faithfully reproduce the author's intention (social intelligence). Machine translation, therefore, is believed to be AI-complete: it may require strong AI to be done as well as humans can do it.[84]

[edit] Approaches to AI

There are as many approaches to AI as there are AI researchers—any coarse categorization is likely to be unfair to someone. Artificial intelligence communities have grown up around particular problems, institutions and researchers, as well as the theoretical insights that define the approaches described below. Artificial intelligence is a young science and is still a fragmented collection of subfields. At present, there is no established unifying theory that links the subfields into a coherent whole.

[edit] Cybernetics and brain simulation

In the 40s and 50s, a number of researchers explored the connection between neurology, information theory, and cybernetics. Some of them built machines that used electronic networks to exhibit rudimentary intelligence, such as W. Grey Walter's turtles and the Johns Hopkins Beast. Many of these researchers gathered for meetings of the Teleological Society at Princeton and the Ratio Club in England.[85]

[edit] Traditional symbolic AI

When access to digital computers became possible in the middle 1950s, AI research began to explore the possibility that human intelligence could be reduced to symbol manipulation. The research was centered in three institutions: CMU, Stanford and MIT, and each one developed its own style of research. John Haugeland named these approaches to AI "good old fashioned AI" or "GOFAI".[86]

Cognitive simulation
Economist Herbert Simon and Alan Newell studied human problem solving skills and attempted to formalize them, and their work laid the foundations of the field of artificial intelligence, as well as cognitive science, operations research and management science. Their research team performed psychological experiments to demonstrate the similarities between human problem solving and the programs (such as their "General Problem Solver") they were developing. This tradition, centered at Carnegie Mellon University,[87] would eventually culminate in the development of the Soar architecture in the middle 80s.[88]
Logical AI
Unlike Newell and Simon, John McCarthy felt that machines did not need to simulate human thought, but should instead try to find the essence of abstract reasoning and problem solving, regardless of whether people used the same algorithms.[89] His laboratory at Stanford (SAIL) focused on using formal logic to solve a wide variety of problems, including knowledge representation, planning and learning. Work in logic led to the development of the programming language Prolog and the science of logic programming.[90]
"Scruffy" symbolic AI
Researchers at MIT (such as Marvin Minsky and Seymour Papert) found that solving difficult problems in vision and natural language processing required ad-hoc solutions – they argued that there was no easy answer, no simple and general principle (like logic) that would capture all the aspects of intelligent behavior. Roger Schank described their "anti-logic" approaches as "scruffy" (as opposed to the "neat" paradigms at CMU and Stanford),[91] and this still forms the basis of research into commonsense knowledge bases (such as Doug Lenat's Cyc) which must be built one complicated concept at a time.
Knowledge based AI
When computers with large memories became available around 1970, researchers from all three traditions began to build knowledge into AI applications. This "knowledge revolution" led to the development and deployment of expert systems (introduced by Edward Feigenbaum), the first truly successful form of AI software.[92] The knowledge revolution was also driven by the realization that truly enormous amounts of knowledge would be required by many simple AI applications.

[edit] Sub-symbolic AI

During the 1960s, symbolic approaches had achieved great success at simulating high-level thinking in small demonstration programs. Approaches based on cybernetics or neural networks were abandoned or pushed into the background.[93] By the 1980s, however, progress in symbolic AI seemed to stall and many believed that symbolic systems would never be able to imitate all the processes of human cognition, especially perception, robotics, learning and pattern recognition. A number of researchers began to look into "sub-symbolic" approaches to specific AI problems.[94]

Bottom-up, situated, behavior based or nouvelle AI
Researchers from the related field of robotics, such as Rodney Brooks, rejected symbolic AI and focussed on the basic engineering problems that would allow robots to move and survive.[95] Their work revived the non-symbolic viewpoint of the early cybernetics researchers of the 50s and reintroduced the use of control theory in AI. These approaches are also conceptually related to the embodied mind thesis.
Computational Intelligence
Interest in neural networks and "connectionism" was revived by David Rumelhart and others in the middle 1980s.[96] These and other sub-symbolic approaches, such as fuzzy systems and evolutionary computation, are now studied collectively by the emerging discipline of computational intelligence.[97]
The new neats
In the 1990s, AI researchers developed sophisticated mathematical tools to solve specific subproblems. These tools are truly scientific, in the sense that their results are both measurable and verifiable, and they have been responsible for many of AI's recent successes. The shared mathematical language has also permitted a high level of collaboration with more established fields (like mathematics, economics or operations research). Russell & Norvig (2003) describe this movement as nothing less than a "revolution" and "the victory of the neats."[98]

[edit] Intelligent agent paradigm

The "intelligent agent" paradigm became widely accepted during the 1990s.[99][100] Although earlier researchers had proposed modular "divide and conquer" approaches to AI,[101] the intelligent agent did not reach its modern form until Judea Pearl, Alan Newell and others brought concepts from decision theory and economics into the study of AI.[102] When the economist's definition of a rational agent was married to computer science's definition of an object or module, the intelligent agent paradigm was complete.

An intelligent agent is a system that perceives its environment and takes actions which maximizes its chances of success. The simplest intelligent agents are programs that solve specific problems. The most complicated intelligent agents would be rational, thinking human beings.[100]

The paradigm gives researchers license to study isolated problems and find solutions that are both verifiable and useful, without agreeing on one single approach. An agent that solves a specific problem can use any approach that works — some agents are symbolic and logical, some are sub-symbolic neural networks and some can be based on new approaches (without forcing researchers to reject old approaches that have proven useful). The paradigm gives researchers a common language to describe problems and share their solutions with each other and with other fields—such as decision theory—that also use concepts of abstract agents.

[edit] Integrating the approaches

An agent architecture or cognitive architecture allows researchers to build more versatile and intelligent systems out of interacting intelligent agents in a multi-agent system.[103] A system with both symbolic and sub-symbolic components is a hybrid intelligent system, and the study of such systems is artificial intelligence systems integration. A hierarchical control system provides a bridge between sub-symbolic AI at its lowest, reactive levels and traditional symbolic AI at its highest levels, where relaxed time constraints permit planning and world modelling.[104] Rodney Brooks' subsumption architecture was an early proposal for such a hierarchical system.

[edit] Tools of AI research

In the course of 50 years of research, AI has developed a large number of tools to solve the most difficult problems in computer science. A few of the most general of these methods are discussed below.

[edit] Search

Main article: search algorithm

Many problems in AI can be solved in theory by intelligently searching through many possible solutions:[105] Reasoning can be reduced to performing a search. For example, logical proof can be viewed as searching for a path that leads from premises to conclusions, where each step is the application of an inference rule.[106] Planning algorithms search through trees of goals and subgoals, attempting to find a path to a target goal.[107] Robotics algorithms for moving limbs and grasping objects use local searches in configuration space.[77] Many learning algorithms have search at their core.[108]

There are several types of search algorithms:

[edit] Logic

Main article: logic programming

Logic[112] was introduced into AI research by John McCarthy in his 1958 Advice Taker proposal. The most important technical development was J. Alan Robinson's discovery of the resolution and unification algorithm for logical deduction in 1963. This procedure is simple, complete and entirely algorithmic, and can easily be performed by digital computers.[113] However, a naive implementation of the algorithm quickly leads to a combinatorial explosion or an infinite loop. In 1974, Robert Kowalski suggested representing logical expressions as Horn clauses (statements in the form of rules: "if p then q"), which reduced logical deduction to backward chaining or forward chaining. This greatly alleviated (but did not eliminate) the problem.[106][114]

Logic is used for knowledge representation and problem solving, but it can be applied to other problems as well. For example, the satplan algorithm uses logic for planning,[115] and inductive logic programming is a method for learning.[116]

There are several different forms of logic used in AI research.

  • Fuzzy logic, a version of first-order logic which allows the truth of a statement to be represented as a value between 0 and 1, rather than simply True (1) or False (0). Fuzzy systems can be used for uncertain reasoning and have been widely used in modern industrial and consumer product control systems.[119]

[edit] Probabilistic methods for uncertain reasoning

Main articles: Bayesian network, hidden Markov model, Kalman filter, decision theory, and utility theory

Many problems in AI (in reasoning, planning, learning, perception and robotics) require the agent to operate with incomplete or uncertain information. Starting in the late 80s and early 90s, Judea Pearl and others championed the use of methods drawn from probability theory and economics to devise a number of powerful tools to solve these problems.[120]

Bayesian networks[121] are very general tool that can be used for a large number of problems: reasoning (using the Bayesian inference algorithm),[122] learning (using the expectation-maximization algorithm),[123] planning (using decision networks)[124] and perception (using dynamic Bayesian networks).[125]

Probabilistic algorithms can also be used for filtering, prediction, smoothing and finding explanations for streams of data, helping perception systems to analyze processes that occur over time[126] (e.g., hidden Markov models[127] and Kalman filters[128]).

Planning problems have also taken advantages of other tools from economics, such as decision theory and decision analysis,[129] information value theory,[68] Markov decision processes,[130] dynamic decision networks,[130] game theory and mechanism design[131]

[edit] Classifiers and statistical learning methods

Main articles: classifier (mathematics), statistical classification, and machine learning

The simplest AI applications can be divided into two types: classifiers ("if shiny then diamond") and controllers ("if shiny then pick up"). Controllers do however also classify conditions before inferring actions, and therefore classification forms a central part of many AI systems.

Classifiers[132] are functions that use pattern matching to determine a closest match. They can be tuned according to examples, making them very attractive for use in AI. These examples are known as observations or patterns. In supervised learning, each pattern belongs to a certain predefined class. A class can be seen as a decision that has to be made. All the observations combined with their class labels are known as a data set.

When a new observation is received, that observation is classified based on previous experience. A classifier can be trained in various ways; there are many statistical and machine learning approaches.

A wide range of classifiers are available, each with its strengths and weaknesses. Classifier performance depends greatly on the characteristics of the data to be classified. There is no single classifier that works best on all given problems; this is also referred to as the "no free lunch" theorem. Various empirical tests have been performed to compare classifier performance and to find the characteristics of data that determine classifier performance. Determining a suitable classifier for a given problem is however still more an art than science.

The most widely used classifiers are the neural network,[133] kernel methods such as the support vector machine,[134] k-nearest neighbor algorithm,[135] Gaussian mixture model,[136] naive Bayes classifier,[137] and decision tree.[108] The performance of these classifiers have been compared over a wide range of classification tasks[138] in order to find data characteristics that determine classifier performance.

[edit] Neural networks

Main articles: neural networks and connectionism
A neural network is an interconnected group of nodes, akin to the vast network of neurons in the human brain.
A neural network is an interconnected group of nodes, akin to the vast network of neurons in the human brain.

The study of artificial neural networks[133] began with cybernetics researchers, working in the decade before the field AI research was founded. In the 1960s Frank Rosenblatt developed an important early version, the perceptron.[139]

Paul Werbos developed the backpropagation algorithm for multilayer perceptrons in 1974,[140] which led to a renaissance in neural network research and connectionism in general in the middle 1980s. Other common network architectures which have been developed include the feedforward neural network, the radial basis network, the Kohonen self-organizing map and various recurrent neural networks. The Hopfield net, a form of attractor network, was first described by John Hopfield in 1982.

Neural networks are applied to the problem of learning, using such techniques as Hebbian learning[141] and the relatively new field of Hierarchical Temporal Memory which simulates the architecture of the neocortex.[142]

[edit] Social and emergent models

Main article: evolutionary computation

Several algorithms for learning use tools from evolutionary computation, such as genetic algorithms,[143][144] swarm intelligence.[145] and genetic programming.[146][147]

[edit] Control theory

Main article: intelligent control

Control theory, the grandchild of cybernetics, has many important applications, especially in robotics.[148]

[edit] Specialized languages

AI researchers have developed several specialized languages for AI research:

AI applications are also often written in standard languages like C++ and languages designed for mathematics, such as Matlab and Lush.

[edit] Evaluating artificial intelligence

Main article: Progress in artificial intelligence

How can one determine if an agent is intelligent? In 1950, Alan Turing proposed a general procedure to test the intelligence of an agent now known as the Turing test. This procedure allows almost all the major problems of artificial intelligence to be tested. However, it is a very difficult challenge and at present all agents fail.

Artificial intelligence can also be evaluated on specific problems such as small problems in chemistry, hand-writing recognition and game-playing. Such tests have been termed subject matter expert Turing tests. Smaller problems provide more achievable goals and there are an ever-increasing number of positive results.

The broad classes of outcome for an AI test are:

  • optimal: it is not possible to perform better
  • strong super-human: performs better than all humans
  • super-human: performs better than most humans
  • sub-human: performs worse than most humans

For example, performance at checkers is optimal,[153] performance at chess is super-human and nearing strong super-human,[154] and performance at many everyday tasks performed by humans is sub-human.

[edit] Competitions and prizes

Main article: Competitions and prizes in artificial intelligence

There are a number of competitions and prizes to promote research in artificial intelligence. The main areas promoted are: general machine intelligence, conversational behaviour, data-mining, driverless cars, robot soccer and games.

[edit] Applications of artificial intelligence

Main article: Applications of artificial intelligence

Artificial intelligence has successfully been used in a wide range of fields including medical diagnosis, stock trading, robot control, law, scientific discovery and toys. Frequently, when a technique reaches mainstream use it is no longer considered artificial intelligence, sometimes described as the AI effect.[155] It may also become integrated into artificial life.

[edit] See also

[edit] Notes

  1. ^ Poole, Mackworth & Goebel 1998, p. 1 (who use the term "computational intelligence" as a synonym for artificial intelligence). Other textbooks that define AI this way include Nilsson (1998), and Russell & Norvig (2003) (who prefer the term "rational agent") and write "The whole-agent view is now widely accepted in the field" (Russell & Norvig 2003, p. 55)
  2. ^ This definition, in terms of goals, actions, perception and environment, is due to Russell & Norvig (2003). Other definitions also include knowledge and learning as additional components.
  3. ^ Abstract Intelligent Agents: Paradigms, Foundations and Conceptualization Problems, A.M. Gadomski, J.M. Zytkow, in "Abstract Intelligent Agent, 2". Printed by ENEA, Rome 1995, ISSN/1120-558X]
  4. ^ Although there is some controversy on this point (see Crevier 1993, p. 50), McCarthy states unequivocally "I came up with the term" in a c|net interview. (See Getting Machines to Think Like Us.)
  5. ^ See John McCarthy, What is Artificial Intelligence?
  6. ^ a b This list of intelligent traits is based on the topics covered by the major AI textbooks, including: Russell & Norvig 2003, Luger & Stubblefield 2004, Poole, Mackworth & Goebel 1998 and Nilsson 1998.
  7. ^ a b General intelligence (strong AI) is discussed by popular introductions to AI, such as: Kurzweil 1999, Kurzweil 2005, Hawkins & Blakeslee 2004
  8. ^ Russell & Norvig 2003, pp. 5-16
  9. ^ See AI Topics: applications
  10. ^ a b Poole, Mackworth & Goebel 1998, p. 1
  11. ^ The name of the journal Intelligent Systems
  12. ^ Russell & Norvig 2003, p. 17
  13. ^ McCorduck 2004, p. 5, Russell & Norvig 2003, p. 939
  14. ^ The Egyptian statue of Amun is discussed by Crevier (1993), p. 1). McCorduck (2004), pp. 6-9) discusses Greek statues. Hermes Trismegistus expressed the common belief that with these statues, craftsman had reproduced "the true nature of the gods", their sensus and spiritus. McCorduck makes the connection between sacred automatons and Mosaic law (developed around the same time), which expressly forbids the worship of robots.
  15. ^ McCorduck 2004, p. 13-14 (Paracelsus)
  16. ^ Needham 1986, p. 53
  17. ^ McCorduck 2004, p. 6
  18. ^ A Thirteenth Century Programmable Robot
  19. ^ McCorduck 2004, p. 17
  20. ^ McCorduck 2004, p. xviii
  21. ^ McCorduck (2004), p. 190-25) discusses Frankenstein and identifies the key ethical issues as scientific hubris and the suffering of the monster, e.g. robot rights.
  22. ^ Robots could demand legal rights
  23. ^ See the Times Online, Human rights for robots? We’re getting carried away
  24. ^ robot rights: Russell Norvig, p. 964
  25. ^ Russell & Norvig (2003), p. 960-961)
  26. ^ Kurzweil 2004
  27. ^ Joseph Weizenbaum (the AI researcher who developed the first chatterbot program, ELIZA) argued in 1976 that the misuse of artificial intelligence has the potential to devalue human life. Weizenbaum: Crevier 1993, pp. 132−144, McCorduck 2004, pp. 356-373, Russell & Norvig 2003, p. 961 and Weizenbaum 1976
  28. ^ a b Singularity, transhumanism: Kurzweil 2005, Russell & Norvig 2003, p. 963
  29. ^ Quoted in McCorduck (2004), p. 401)
  30. ^ Among the researchers who laid the foundations of the theory of computation, cybernetics, information theory and neural networks were Claude Shannon, Norbert Weiner, Warren McCullough, Walter Pitts, Donald Hebb, Donald McKay, Alan Turing and John Von Neumann. McCorduck 2004, pp. 51-107, Crevier 1993, pp. 27-32, Russell & Norvig 2003, pp. 15,940, Moravec 1988, p. 3.
  31. ^ Crevier 1993, pp. 47-49, Russell & Norvig 2003, p. 17
  32. ^ Russell and Norvig write "it was astonishing whenever a computer did anything kind of smartish." Russell & Norvig 2003, p. 18
  33. ^ Crevier 1993, pp. 52-107, Moravec 1988, p. 9 and Russell & Norvig 2003, p. 18-21. The programs described are Daniel Bobrow's STUDENT, Newell and Simon's Logic Theorist and Terry Winograd's SHRDLU.
  34. ^ Crevier 1993, pp. 64-65
  35. ^ Simon 1965, p. 96 quoted in Crevier 1993, p. 109
  36. ^ Minsky 1967, p. 2 quoted in Crevier 1993, p. 109
  37. ^ See History of artificial intelligence — the problems.
  38. ^ Crevier 1993, pp. 115-117, Russell & Norvig 2003, p. 22, NRC 1999 under "Shift to Applied Research Increases Investment." and also see Howe, J. "Artificial Intelligence at Edinburgh University: a Perspective"
  39. ^ Crevier 1993, pp. 161-162,197-203 and Russell & Norvig 2003, p. 24
  40. ^ Crevier 1993, p. 203
  41. ^ Crevier 1993, pp. 209-210
  42. ^ Russell Norvig, p. 28,NRC 1999 under "Artificial Intelligence in the 90s"
  43. ^ Russell Norvig, pp. 25-26
  44. ^ All of these positions are mentioned in standard discussions of the subject, such as Russell & Norvig 2003, pp. 947-960 and Fearn 2007, pp. 38-55
  45. ^ Turing 1950, Haugeland 1985, pp. 6-9, Crevier 1993, p. 24, Russell & Norvig 2003, pp. 2-3 and 948
  46. ^ McCarthy et al. 1955 See also Crevier 1993, p. 28
  47. ^ Newell & Simon 1963 and Russell & Norvig 2003, p. 18
  48. ^ Dreyfus criticized a version of the physical symbol system hypothesis that he called the "psychological assumption": "The mind can be viewed as a device operating on bits of information according to formal rules". Dreyfus 1992, p. 156. See also Dreyfus & Dreyfus 1986, Russell & Norvig 2003, pp. 950-952, Crevier & 1993 120-132 and Hearn 2007, pp. 50-51
  49. ^ This is a paraphrase of the most important implication of Gödel's theorems, according Hofstadter (1979). See also Russell & Norvig 2003, p. 949, Gödel 1931, Church 1936, Kleene 1935, Turing 1937, Turing 1950 under “(2) The Mathematical Objection”
  50. ^ Searle 1980. See also Russell & Norvig (2003), p. 947): "The assertion that machines could possibly act intelligently (or, perhaps better, act as if they were intelligent) is called the 'weak AI' hypothesis by philosophers, and the assertion that machines that do so are actually thinking (as opposed to simulating thinking) is called the 'strong AI' hypothesis," although Searle's arguments, such as the Chinese Room, apply only to physical symbol systems, not to machines in general (he would consider the brain a machine). Also, notice that the positions as Searle states them don't make any commitment to how much intelligence the system has: it is one thing to say a machine can act intelligently, it is another to say it can act as intelligently as a human being.
  51. ^ Moravec 1988 and Kurzweil 2005, p. 262. Also see Russell Norvig, p. 957 and Crevier 1993, pp. 271 and 279. The most extreme form of this argument (the brain replacement scenario) was put forward by Clark Glymour in the mid-70s and was touched on by Zenon Pylyshyn and John Searle in 1980.
  52. ^ "We cannot yet characterize in general what kinds of computational procedures we want to call intelligent." John McCarthy, Basic Questions
  53. ^ Problem solving, puzzle solving, game playing and deduction: Russell & Norvig 2003, chpt. 3-9, Poole et al. chpt. 2,3,7,9, Luger & Stubblefield 2004, chpt. 3,4,6,8, Nilsson, chpt. 7-12.
  54. ^ Uncertain reasoning: Russell & Norvig 2003, pp. 452-644, Poole, Mackworth & Goebel 1998, pp. 345-395, Luger & Stubblefield 2004, pp. 333-381, Nilsson 1998, chpt. 19
  55. ^ Intractability and efficiency and the combinatorial explosion: Russell & Norvig 2003, pp. 9, 21-22
  56. ^ Several famous examples: Wason (1966) showed that people do poorly on completely abstract problems, but if the problem is restated to allowed the use of intuitive social intelligence, performance dramatically improves. (See Wason selection task) Tversky, Slovic & Kahnemann (1982) have shown that people are terrible at elementary problems that involve uncertain reasoning. (See list of cognitive biases for several examples). Lakoff & Nunez (2000) have controversially argued that even our skills at mathematics depend on knowledge and skills that come from "the body", i.e. sensorimotor and perceptual skills. (See Where Mathematics Comes From)
  57. ^ Knowledge representation: ACM 1998, I.2.4, Russell & Norvig 2003, pp. 320-363, Poole, Mackworth & Goebel 1998, pp. 23-46, 69-81, 169-196, 235-277, 281-298, 319-345, Luger & Stubblefield 2004, pp. 227-243, Nilsson 1998, chpt. 18
  58. ^ Knowledge engineering: Russell & Norvig 2003, pp. 260-266, Poole, Mackworth & Goebel 1998, pp. 199-233, Nilsson 1998, chpt. ~17.1-17.4
  59. ^ a b Representing categories and relations: Semantic networks, description logics, inheritance (including frames and scripts): Russell & Norvig 2003, pp. 349-354, Poole, Mackworth & Goebel 1998, pp. 174-177, Luger & Stubblefield 2004, pp. 248-258, Nilsson 1998, chpt. 18.3
  60. ^ a b Representing events and time: Situation calculus, event calculus, fluent calculus (including solving the frame problem): Russell & Norvig 2003, pp. 328-341, Poole, Mackworth & Goebel 1998, pp. 281-298, Nilsson 1998, chpt. 18.2
  61. ^ a b Causal calculus: Poole, Mackworth & Goebel 1998, pp. 335-337
  62. ^ a b Representing knowledge about knowledge: Belief calculus, modal logics: Russell & Norvig 2003, pp. 341-344, Poole, Mackworth & Goebel 1998, pp. 275-277
  63. ^ Ontology: Russell & Norvig 2003, pp. 320-328
  64. ^ McCarthy & Hayes 1969
  65. ^ a b Default reasoning and default logic, non-monotonic logics, circumscription, closed world assumption, abduction (Poole et al. places abduction under "default reasoning". Luger et al. places this under "uncertain reasoning"): Russell & Norvig 2003, pp. 354-360, Poole, Mackworth & Goebel 1998, pp. 248-256, 323-335, Luger & Stubblefield 2004, pp. 335-363, Nilsson 1998, ~18.3.3
  66. ^ Crevier 1993, pp. 113-114, Moravec 1988, p. 13, Lenat 1989 (Introduction), Russell & Norvig 2003, p. 21
  67. ^ Planning: ACM 1998, ~I.2.8, Russell & Norvig 2003, pp. 375-459, Poole, Mackworth & Goebel 1998, pp. 281-316, Luger & Stubblefield 2004, pp. 314-329, Nilsson 1998, chpt. 10.1-2, 22
  68. ^ a b Information value theory: Russell & Norvig 2003, pp. 600-604
  69. ^ Classical planning: Russell & Norvig 2003, pp. 375-430, Poole, Mackworth & Goebel 1998, pp. 281-315, Luger & Stubblefield 2004, pp. 314-329, Nilsson 1998, chpt. 10.1-2, 22
  70. ^ Planning and acting in non-deterministic domains: conditional planning, execution monitoring, replanning and continuous planning: Russell & Norvig 2003, pp. 430-449
  71. ^ Multi-agent planning and emergent behavior: Russell & Norvig 2003, pp. 449-455
  72. ^ Learning: ACM 1998, I.2.6, Russell & Norvig 2003, pp. 649-788, Poole, Mackworth & Goebel 1998, pp. 397-438, Luger & Stubblefield 2004, pp. 385-542, Nilsson 1998, chpt. 3.3 , 10.3, 17.5, 20
  73. ^ Reinforcement learning: Russell & Norvig 2003, pp. 763-788, Luger & Stubblefield 2004, pp. 442-449
  74. ^ Natural language processing: ACM 1998, I.2.7, Russell & Norvig 2003, pp. 790-831, Poole, Mackworth & Goebel 1998, pp. 91-104, Luger & Stubblefield 2004, pp. 591-632
  75. ^ Applications of natural language processing, including information retrieval (i.e. text mining) and machine translation Russell & Norvig 2003, pp. 840-857, Luger & Stubblefield 2004, pp. 623-630
  76. ^ Robotics: ACM 1998, I.2.9, Russell & Norvig 2003, pp. 901-942, Poole, Mackworth & Goebel 1998, pp. 443-460
  77. ^ a b Moving and configuration space: Russell Norivg, pp. 916-932
  78. ^ Robotic mapping (localization, etc) Russell Norvig, pp. 908-915
  79. ^ Machine perception: Russell & Norvig 2003, pp. 537-581, 863-898, Nilsson 1998, ~chpt. 6
  80. ^ Computer vision: ACM 1998, I.2.10, Russell & Norvig 2003, pp. 863-898, Nilsson 1998, chpt. 6
  81. ^ Speech recognition: ACM 1998, ~I.2.7, Russell & Norvig 2003, pp. 568-578
  82. ^ Object recognition: Russell & Norvig 2003, pp. 885-892
  83. ^ Minsky 2007, Picard 1997
  84. ^ Shapiro 1992, p. 9
  85. ^ Among the researchers who laid the foundations of cybernetics, information theory and neural networks were Claude Shannon, Norbert Weiner, Warren McCullough, Walter Pitts, Donald Hebb, Donald McKay, Alan Turing and John Von Neumann. McCorduck 2004, pp. 51-107 Crevier 1993, pp. 27-32, Russell & Norvig 2003, pp. 15,940, Moravec 1988, p. 3.
  86. ^ Haugeland 1985, pp. 112-117
  87. ^ Then called Carnegie Tech
  88. ^ Crevier 1993, pp. 52-54, 258-263, Nilsson 1998, p. 275
  89. ^ See Science at Google Books, and McCarthy's presentation at AI@50
  90. ^ Crevier 1993, pp. 193-196
  91. ^ Crevier 1993, pp. 163-176. Neats vs. scruffies: Crevier 1993, pp. 168.
  92. ^ Crevier 1993, pp. 145-162
  93. ^ The most dramatic case of sub-symbolic AI being pushed into the background was the devastating critique of perceptrons by Marvin Minsky and Seymour Papert in 1969. See History of AI, AI winter, or Frank Rosenblatt. (Crevier 1993, pp. 102-105).
  94. ^ Nilsson (1998), p. 7) characterizes these newer approaches to AI as "sub-symbolic".
  95. ^ Brooks 1990 and Moravec 1988
  96. ^ Crevier 1993, pp. 214-215 and Russell & Norvig 2003, p. 25
  97. ^ See IEEE Computational Intelligence Society
  98. ^ Russell & Norvig 2003, p. 25-26
  99. ^ "The whole-agent view is now widely accepted in the field" Russell & Norvig 2003, p. 55.
  100. ^ a b The intelligent agent paradigm is discussed in major AI textbooks, such as: Russell & Norvig 2003, pp. 27, 32-58, 968-972, Poole, Mackworth & Goebel 1998, pp. 7-21, Luger & Stubblefield 2004, pp. 235-240
  101. ^ For example, both John Doyle (Doyle 1983) and Marvin Minsky's popular classic The Society of Mind (Minsky 1986) used the word "agent" to describe modular AI systems.
  102. ^ Russell & Norvig 2003, pp. 27, 55
  103. ^ Agent architectures, hybrid intelligent systems, and multi-agent systems: ACM 1998, I.2.11, Russell & Norvig (1998), pp. 27, 932, 970-972) and Nilsson (1998, chpt. 25)
  104. ^ Albus, J. S. 4-D/RCS reference model architecture for unmanned ground vehicles. In G Gerhart, R Gunderson, and C Shoemaker, editors, Proceedings of the SPIE AeroSense Session on Unmanned Ground Vehicle Technology, volume 3693, pages 11—20
  105. ^ Search algorithms: Russell & Norvig 2003, pp. 59-189, Poole, Mackworth & Goebel 1998, pp. 113-163, Luger & Stubblefield 2004, pp. 79-164, 193-219, Nilsson 1998, chpt. 7-12
  106. ^ a b Forward chaining, backward chaining, Horn clauses, and logical deduction as search: Russell & Norvig 2003, pp. 217-225, 280-294, Poole, Mackworth & Goebel 1998, pp. ~46-52, Luger & Stubblefield 2004, pp. 62-73, Nilsson 1998, chpt. 4.2, 7.2
  107. ^ State space search and planning: Russell & Norvig 2003, pp. 382-387, Poole, Mackworth & Goebel 1998, pp. 298-305, Nilsson 1998, chpt. 10.1-2
  108. ^ a b Decision tree: Russell & Norvig 2003, pp. 653-664, Poole, Mackworth & Goebel 1998, pp. 403-408, Luger & Stubblefield 2004, pp. 408-417
  109. ^ Naive searches (breadth first search, depth first search and general state space search): Russell & Norvig 2003, pp. 59-93, Poole, Mackworth & Goebel 1998, pp. 113-132, Luger & Stubblefield 2004, pp. 79-121, Nilsson 1998, chpt. 8
  110. ^ Heuristic or informed searches (e.g., greedy best first and A*): Russell & Norvig 2003, pp. 94-109, Poole, Mackworth & Goebel 1998, pp. pp. 132-147, Luger & Stubblefield 2004, pp. 133-150, Nilsson 1998, chpt. 9
  111. ^ Optimization searches: Russell & Norvig 2003, pp. 110-116,120-129, Poole, Mackworth & Goebel 1998, pp. 56-163, Luger & Stubblefield 2004, pp. 127-133
  112. ^ Logic: ACM 1998, ~I.2.3, Russell & Norvig 2003, pp. 194-310, Luger & Stubblefield 2004, pp. 35-77, Nilsson 1998, chpt. 13-16
  113. ^ Resolution and unification: Russell & Norvig 2003, pp. 213-217, 275-280, 295-306, Poole, Mackworth & Goebel 1998, pp. 56-58, Luger & Stubblefield 2004, pp. 554-575, Nilsson 1998, chpt. 14 & 16
  114. ^ a b History of logic programming: Crevier 1993, pp. 190-196. Advice Taker: McCorduck 2004, p. 51, Russell & Norvig 2003, pp. 19
  115. ^ Satplan: Russell & Norvig 2003, pp. 402-407, Poole, Mackworth & Goebel 1998, pp. 300-301, Nilsson 1998, chpt. 21
  116. ^ Explanation based learning, relevance based learning, inductive logic programming, case based reasoning: Russell & Norvig 2003, pp. 678-710, Poole, Mackworth & Goebel 1998, pp. 414-416, Luger & Stubblefield 2004, pp. ~422-442, Nilsson 1998, chpt. 10.3, 17.5
  117. ^ Propositional logic: Russell & Norvig 2003, pp. 204-233, Luger & Stubblefield 2004, pp. 45-50 Nilsson 1998, chpt. 13
  118. ^ First-order logic and features such as equality: ACM 1998, ~I.2.4, Russell & Norvig 2003, pp. 240-310, Poole, Mackworth & Goebel 1998, pp. 268-275, Luger & Stubblefield 2004, pp. 50-62, Nilsson 1998, chpt. 15
  119. ^ Fuzzy logic: Russell & Norvig 2003, pp. 526-527
  120. ^ Russell & Norvig 2003, pp. 25-26 (on Judea Pearl's contribution). Stochastic methods are described in all the major AI textbooks: ACM 1998, ~I.2.3, Russell & Norvig 2003, pp. 462-644, Poole, Mackworth & Goebel 1998, pp. 345-395, Luger & Stubblefield 2004, pp. 165-191, 333-381, Nilsson 1998, chpt. 19
  121. ^ Bayesian networks: Russell & Norvig 2003, pp. 492-523, Poole, Mackworth & Goebel 1998, pp. 361-381, Luger & Stubblefield 2004, pp. ~182-190, ~363-379, Nilsson 1998, chpt. 19.3-4
  122. ^ Bayesian inference algorithm: Russell & Norvig 2003, pp. 504-519, Poole, Mackworth & Goebel 1998, pp. 361-381, Luger & Stubblefield 2004, pp. ~363-379, Nilsson 1998, chpt. 19.4 & 7
  123. ^ Bayesian learning and the expectation-maximization algorithm: Russell & Norvig 2003, pp. 712-724, Poole, Mackworth & Goebel 1998, pp. 424-433, Nilsson 1998, chpt. 20
  124. ^ Bayesian decision networks: Russell & Norvig 2003, pp. 597-600
  125. ^ Dynamic Bayesian network: Russell & Norvig 2003, pp. 551-557
  126. ^ Russell & Norvig 2003, pp. 537-581
  127. ^ Hidden Markov model: Russell & Norvig 2003, pp. 549-551
  128. ^ Kalman filter: Russell & Norvig 2003, pp. 551-557
  129. ^ decision theory and decision analysis: Russell & Norvig 2003, pp. 584-597, Poole, Mackworth & Goebel 1998, pp. 381-394
  130. ^ a b Markov decision processes and dynamic decision networks:Russell & Norvig 2003, pp. 613-631
  131. ^ Game theory and mechanism design: Russell & Norvig 2003, pp. 631-643
  132. ^ Statistical learning methods and classifiers: Russell & Norvig 2003, pp. 712-754, Luger & Stubblefield 2004, pp. 453-541
  133. ^ a b Neural networks and connectionism: Russell & Norvig 2003, pp. 736-748, Poole, Mackworth & Goebel 1998, pp. 408-414, Luger & Stubblefield 2004, pp. 453-505, Nilsson 1998, chpt. 3
  134. ^ Kernel methods: Russell & Norvig 2003, pp. 749-752
  135. ^ K-nearest neighbor algorithm: Russell & Norvig 2003, pp. 733-736
  136. ^ Gaussian mixture model: Russell & Norvig 2003, pp. 725-727
  137. ^ Naive Bayes classifier: Russell & Norvig 2003, pp. 718
  138. ^ van der Walt, Christiaan. Data characteristics that determine classifier performance.
  139. ^ Perceptrons: Russell & Norvig 2003, pp. 740-743, Luger & Stubblefield 2004, pp. 458-467
  140. ^ Backpropagation: Russell & Norvig 2003, pp. 744-748, Luger & Stubblefield 2004, pp. 467-474, Nilsson 1998, chpt. 3.3
  141. ^ Competitive learning, Hebbian coincidence learning, Hopfield networks and attractor networks: Luger & Stubblefield 2004, pp. 474-505.
  142. ^ Hawkins & Blakeslee 2004
  143. ^ Holland, John H. (1975). Adaptation in Natural and Artificial Systems. University of Michigan Press. ISBN 0262581116. 
  144. ^ Genetic algorithms for learning: Luger & Stubblefield 2004, pp. 509-530, Nilsson 1998, chpt. 4.2
  145. ^ Artificial life and society based learning: Luger & Stubblefield 2004, pp. 530-541
  146. ^ Koza, John R. (1992). Genetic Programming. MIT Press. 
  147. ^ Poli, R., Langdon, W. B., McPhee, N. F. (2008). A Field Guide to Genetic Programming. Lulu.com, freely available from http://www.gp-field-guide.org.uk/. ISBN 978-1-4092-0073-4. 
  148. ^ Control theory: ACM 1998, ~I.2.8, Russell & Norvig 2003, pp. 926-932
  149. ^ Crevier 1993, p. 46-48
  150. ^ Lisp: Luger & Stubblefield 2004, pp. 723-821
  151. ^ Crevier 1993, pp. 59-62, Russell & Norvig 2003, p. 18
  152. ^ Prolog: Poole, Mackworth & Goebel 1998, pp. 477-491, Luger & Stubblefield 2004, pp. 641-676, 575-581
  153. ^ Schaeffer, Jonathan (2007-07-19). Checkers Is Solved. Science. Retrieved on 2007-07-20.
  154. ^ Computer Chess#Computers versus humans
  155. ^ AI set to exceed human brain power (web article). CNN.com (2006-07-26). Retrieved on 2008-02-26.

[edit] References

[edit] Major AI textbooks

[edit] Other sources

[edit] Further reading

  • R. Sun & L. Bookman, (eds.), Computational Architectures: Integrating Neural and Symbolic Processes. Kluwer Academic Publishers, Needham, MA. 1994.

[edit] External links

 The external links in this article may not follow Wikipedia's content policies or guidelines.
Please improve this article by removing excessive or inappropriate external links.
Find more about Artificial Intelligence on Wikipedia's sister projects:
Dictionary definitions
Textbooks
Quotations
Source texts
Images and media
News stories
Learning resources
v • d • e
Major fields of technology
Applied science
Information
Industry
Military
Domestic
Engineering
Health and safety
Transport