Artificial intelligence

From Includipedia, the inclusionist encyclopedia

Jump to: navigation, search
"AI" redirects here. For other uses of "AI" and "Artificial intelligence", see AI (disambiguation).
Image:P11 kasparov breakout.jpg
Garry Kasparov playing against Deep Blue, the first machine to win a chess match against a reigning world champion.

The modern definition of artificial intelligence (or AI) is "the study and design of intelligent agents" where an intelligent agent is a system that perceives its environment and takes actions which maximizes its chances of success.[1] John McCarthy, who coined the term in 1956,[2] defines it as "the science and engineering of making intelligent machines."[3] Other names for the field have been proposed, such as computational intelligence,[4] synthetic intelligence[4] or computational rationality.[5]

The term artificial intelligence is also used to describe a property of machines or programs: the intelligence that the system demonstrates. 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, 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]

Artificial intelligence Portal

Contents

[edit] Perspectives on AI

Image:PygmalianGalatea.jpg
Pygmalion and Galatea (1890) by Jean-Léon Gérôme (1824–1904)

[edit] History of AI

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

Samuel Butler first raised the possibility of "mechanical consciousness" in an article signed with the nom de plume Cellarius and headed "Darwin among the Machines", which appeared in the Christchurch, New Zealand, newspaper The Press on 13 June 1863. [10] Butler envisioned mechanical consciousness emerging by means of Darwinian Evolution, specifically by Natural selection, as a form of natural, not artificial, intelligence.

Template:Harvtxt, however, writes "Artificial intelligence in one form or another is an idea that has pervaded Western intellectual history, a dream in urgent need of being realized." She continues:

"Work toward that end has been a splendid effort, the variety of its form as wondrous as anything humans have conceived; its practitioners as lively a group of poets, dreamers, holy men, rascals, and assorted eccentrics as one could hope to find—not a dullard among them. Its visionaries have lifted our spirits and made us transcend our own species, its poets have told us things about ourselves we never suspected, and its fast talkers have set everybody's teeth on edge."[11]

Beginning with the myth of Pygmalian and Galatea, we have imagined making copies of ourselves, with sacred statues, alchemical beings and charming clockwork automatons.[12] Yet we also have a fear that our creations may turn on us, as in The Golem of Prague and Frankenstein.

In the middle of the 20th century, a handful of scientists explored a new approach to an ancient dream, based on their 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.[13]

In the summer of 1956, at a conference on the campus of Dartmouth College, the field of AI research was born.[14] 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:[15] computers were solving word problems in algebra, proving logical theorems and speaking English.[16] By the middle 60s their research was heavily funded by DARPA[17] 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"[18]
  • 1967, Marvin Minsky: "Within a generation ... the problem of creating 'artificial intelligence' will substantially be solved."[19]

These predictions, and many like them, would not come true. They had failed to recognize the difficulty of some of the problems they faced.[20] In 1974, in response to the criticism of England's Sir James Lighthill and ongoing pressure from Congress to fund more productive projects, DARPA cut off all undirected, exploratory research in AI. This was the first AI Winter.[21]

In the early 80s, the field was revived by the commercial success of expert systems and by 1985 the market for AI had reached more than a billion dollars.[22] Minsky and others warned the community that enthusiasm for AI had spiraled out of control and that disappointment was sure to follow.[23] Minsky was right. 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.[24]

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.[25] 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.[26]

[edit] Philosophy of AI

Mind and Brain Portal
Main article: philosophy of artificial intelligence
Image:User-FastFission-brain.gif
Can the brain be simulated? Does this prove machines can think?

The philosophy of artificial intelligence considers the question "Can machines think?" Alan Turing, in his classic 1950 paper, Computing Machinery and Intelligence, was the first to try to answer it. In the years since, several answers have been given:[27]

  • Turing's "polite convention": If a machine acts as intelligently as a human being, then it is as intelligent as a human being.[28]
  • The Dartmouth proposal: Every aspect of learning or any other feature of intelligence can be so precisely described that a machine can be made to simulate it. This assertion was printed in the program for the Dartmouth Conference of 1956, and represents the position of most working AI researchers.[29]
  • Newell and Simon's physical symbol system hypothesis: A physical symbol system has the necessary and sufficient means of general intelligent action. This statement claims that essence of intelligence is symbol manipulation.[30]
  • The artificial brain argument: The brain can be simulated. This argument combines the idea that a Turing complete machine can simulate any process, with the materialist idea that the mind is the result of a physical process in the brain.[31]
  • Gödel's incompleteness theorem: There are statements that no physical symbol system can prove. Roger Penrose is among those who claim that Gödel's theorem limits what machines can do.[32]
  • Dreyfus' "psychological assumption": The mind can be viewed as a device operating on bits of information according to formal rules. Dreyfus refuted this statement by showing that human expertise depends on unconscious instinct rather than conscious symbol manipulation and on having a "feel" for the situation rather explicit symbolic knowledge.[33]
  • Searle's "strong AI position": A physical symbol system can have a mind and mental states. Searle refuted this with his Chinese room argument, which asks us to look inside the computer and try to find where the "mind" might be.[34]

[edit] AI in fiction

Main article: Artificial intelligence in fiction
Image:Hal-9000.jpg
HAL 9000's iconic camera eye.

In modern science fiction, AI are not necessarily limited by the fundamental problems of perception, knowledge representation, common sense reasoning, or learning. This allows speculation on the technology's potential impact on humanity, meditations on metaphysics or the nature of awareness, and the use of novel plot devices. AI has appeared in fiction as a servant (R2D2), a comrade (Lt. Commander Data), a technology expanding human ability (Ghost in the Shell), a conqueror (With Folded Hands), an exterminator (Terminator, Battlestar Galactica), a manager (Portal (video game)). Some realistic potential consequences of AI investigated in fiction are decreased labor demand, the enhancement of human ability or experience, and a need for redefinition of human identity and basic values (or a threat to existing identity and values). (See the Uncanny Valley hypothesis.) One area of speculation focuses on potential disaster. (See AI and Society in fiction)

Though in fiction AI are often aware and capable of feeling, the phenomena that allow these experiences are not understood, and as such, there is no theoretical basis for their synthesis. Current theories provide for machines that can replicate or surpass all external human behavior, but not necessarily human experience.

An AI can play any role traditionally assigned to humans in a narrative, such as that of protagonist (Bicentennial Man), antagonist (Terminator, HAL 9000), faithful companion (R2D2), or comic relief (C3PO). (See Sentient AI in fiction.)

Many portrayals of AI in science fiction deal either with person-like or sentient AI, but the technology of AI appears in many other forms. (See non-sentient AI in fiction.)

The inevitability of the integration of AI into human society is also argued by some science/futurist writers such as Kevin Warwick and Hans Moravec and the manga Ghost in the Shell

[edit] AI research

[edit] Problems of AI

While there is no universally accepted definition of intelligence,[35] 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.[36] 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.[37]

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.[38]

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.[39] 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.

[edit] Knowledge representation

Main articles: knowledge representation and commonsense knowledge

Knowledge representation[40] and knowledge engineering[41] 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;[42] situations, events, states and time;[43] causes and effects;[44] knowledge about knowledge (what we know about what other people know);[45] and many other, less well researched domains. A complete representation of "what exists" is an ontology[46] (borrowing a word from traditional philosophy). Ontological engineering is the science of finding a general representation that can handle all of human knowledge.

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 a 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[47] 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.[48]
  • 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.[49]

[edit] Planning

Main article: automated planning and scheduling

Intelligent agents must be able set goals and achieve them.[50] 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. There are several types of planning problems:

  • Classical planning problems assume that the agent is the only thing acting on the world, and that the agent can be certain what the consequences of it's actions may be.[51] Partial order planning problems take into account the fact that sometimes it's not important which sub-goal the agent achieves first.[52]
  • If the environment is changing, or if the agent can't be sure of the results of its actions, it must periodically check if the world matches its predictions (conditional planning and execution monitoring) and it must change its plan as this becomes necessary (replanning and continuous planning).[53]
  • Some planning problems take into account the utility or "usefulness" of a given outcome. These problems can be analyzed using tools drawn from economics, such as decision theory or decision analysis[54] and information value theory.[55]
  • Multi-agent planning problems try to determine the best plan for a community of agents, using cooperation and competition to achieve a given goal.[56] These problems are related to emerging fields like evolutionary algorithms and swarm intelligence.

[edit] Learning

Main article: machine learning

Important machine learning[57] 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:[58] 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[59] gives machines the ability to be read and understand the languages human beings speak. The problem of natural language processing involves such subproblems as: syntax and parsing;[60] semantics and disambiguation;[61] and discourse understanding.[62] 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.[63]

[edit] Perception

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

Machine perception[64] 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[65] is the ability to analyze visual input. A few selected subproblems are speech recognition,[66] facial recognition and object recognition.[67]

[edit] Motion and manipulation

Main article: robotics

The field of robotics[68] is closely related to AI. Intelligence is required for robots to be able to handle such tasks as:

[edit] Social intelligence

Main article: affective computing
Image:Wikimania 2006 POLIMEREK 100-0093 IMG.JPG
Kismet, a robot with rudimentary social skills.

Emotion and social skills play two roles for an intelligent agent:[71]

  • 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] 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.[72]

[edit] General limitations

There are three general limitations in AI, commonly stated as stupidity, ignorance, and laziness.[citation needed] Most real-world problems have one or more of these factors.

  • Stupidity: One does not always know how to compute a perfect solution.
    E.g. there is no known method to directly factor the multiple of two primes.
    The solution to stupidity is generally to use an alternative method to approach the answer, or one that results in an answer that is "good enough". E.g. for prime factorization, there are various heuristics to determine whether a large number is prime.
  • Ignorance: One does not always have the necessary information to compute a perfect solution.
    E.g. in the game Stratego, the opponent's pieces are of known position, but start as of unknown identity. In Texas hold 'em poker, the order of the deck and thus the other players' cards as well as the flop cards are unknown.
    The solution to ignorance is generally the strategic discovery of new information or acceptance of unknowns - e.g. in Stratego one can bait or attack pieces to uncover their identity, or guess that the opponent's flag is in a well-protected location rather than in an easily reachable one. In poker, one can try to determine the other players' cards by their reactions during bidding, as well as knowing the simple probability of various flop cards and going with whatever is most likely to succeed overall.
  • Laziness: One does not always have the time to compute a perfect solution.
    E.g. in chess, though the state is entirely known, as well as the rules of the game and the value of its outcomes, there is not enough computing power available to exhaustively go through all possible games. Checkers, however, has been solved relatively recently by exactly this method.[citation needed]
    The solution to laziness is generally a utility heuristic - e.g. in chess, one can take a guess at how likely a certain move is to result in a win or a loss even without having fully computed its outcomes, based on generalized ideas such as defensive positions, numeric piece values, etc.

[edit] Approaches to AI

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.[73]

[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".[74]

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,[75] would eventually culminate in the development of the Soar architecture in the middle 80s.[76]
Logical AI 
Unlike Newell and Simon, John McCarthy felt that machines did not need to simulate human thought, but should instead try find the essence of abstract reasoning and problem solving, regardless of whether people used the same algorithms.[77] His laboratory at Stanford (SAIL) focussed on using formal logic to solve 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.[78]
"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 silver bullet, no simple and general principle (like logic) that would capture all the aspects of intelligent behavior. An important realization was that AI required large amounts of commonsense knowledge, and that this had to be engineered one complicated concept at a time. Roger Schank described their "anti-logic" approaches as "scruffy" (as opposed to the "neat" paradigms at CMU and Stanford),[79] and this still forms the basis of research into commonsense knowledge, such as Doug Lenat's Cyc.
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, the first truly successful form of AI software.[80]

[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.[81] 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.[82]

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.[83] 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 "bottom-up" approaches are known as behavior-based AI, situated AI or Nouvelle AI, and are closely tied to embodied cognitive science.
Computational Intelligence 
Interest in neural networks and "connectionism" was revived by David Rumelhart and others in the middle 1980s.[84] These and other sub-symbolic approaches, such as fuzzy systems and evolutionary computation, are now studied collectively by the emerging discipline of computational intelligence.[85]
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). Template:Harvtxt describe this movement as nothing less than a "revolution" and "the victory of the neats."[86]

[edit] Intelligent agent paradigm

The "intelligent agent" paradigm became widely accepted during the 1990s.[87][88] Although earlier researchers had proposed modular "divide and conquer" approaches to AI,[89] 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.[90] 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.[88]

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.[91] 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.

[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:[92]

There are several types of search algorithms:

[edit] Logic

Main article: logic programming

Logic[105] 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.[106] 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.[94][107]

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,[108] and inductive logic programming is a method for learning.[109]

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

[edit] Stochastic methods

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

Starting in the late 80s and early 90s, Judea Pearl and others championed the use of stochastic or probabilistic methods in artificial intelligence.[113] Researchers have used principles from probability theory[114] to devise a number of powerful tools.

Bayesian networks[115] have been applied to a large number of problems, such as: uncertain reasoning (using the Bayesian inference algorithm),[116] learning (using the expectation-maximization algorithm),[117] and planning (using decision networks).[118]

Probabilistic methods have been particularly successful at dealing with processes that occur over time. Several successful algorithms have been developed for filtering, prediction, smoothing and finding explanations for streams of data,[119] such as hidden Markov models,[120] Kalman filters[121] and dynamic Bayesian networks.[122] These tools are used for the problems of perception (such as pattern matching) and learning.

[edit] Economic models

Main articles: utility theory, decision theory, and game theory

AI has been able to use tools drawn from economics, such as decision theory and decision analysis,[54] Bayesian decision networks,[118] information value theory,[55] Markov decision processes,[123] dynamic decision networks,[123] game theory and mechanism design[124] These tools have been especially important for planning problems.

[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[125] 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 mainly 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,[126] kernel methods such as the support vector machine,[127] k-nearest neighbor algorithm,[128] Gaussian mixture model,[129] naive Bayes classifier,[130] and decision tree.[131] The performance of these classifiers have been compared over a wide range of classification tasks[132] in order to find data characteristics that determine classifier performance.

[edit] Neural networks

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

The study of neural networks[126] 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.[133] Paul Werbos discovered the backpropagation algorithm in 1974,[134] which led to a renaissance in neural network research and connectionism in general in the middle 1980s. 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[135] and the relatively new field of Hierarchical Temporal Memory which simulates the architecture of the neocortex.[136]

[edit] Social and emergent models

Main article: evolutionary computation

Several algorithms for learning use tools from evolutionary computation, such as genetic algorithms[137] and swarm intelligence.[138]

[edit] Control theory

Main article: intelligent control

Control theory, the grandchild of cybernetics, has many important applications, especially in robotics.[139]

[edit] Specialized languages

Main articles: IPL, Lisp (programming language), Prolog, STRIPS, and Planner

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] Competitions and prizes

Image:Robocup.legged.leauge.2004.nk.jpg
A legged league game from RoboCup 2004 in Lisbon, Portugal.

The Loebner prize is an annual competition to determine the best Turing test competitors. The winner is the computer system that, in the judges' opinions, demonstrates the "most human" conversational behaviour (with learning AI Ultra Hal winning in 2007, Jabberwacky in 2005 and 2006, and A.L.I.C.E. before that), they have an additional prize for a system that in their opinion passes a Turing test. This second prize has not yet been awarded.

The DARPA Grand Challenge is an annual race for a $2 million prize where driverless cars must travel over a hundred miles without any communication with humans, using GPS, computers and a sophisticated array of sensors. The challenge is aimed at a congressional mandate stating that by 2015 one-third of the operational ground combat vehicles of the US Armed Forces should be unmanned.[144] In November 2007, DARPA introduced the DARPA Urban Challenge, a sixty-mile urban area race.

A popular challenge amongst AI research groups is the RoboCup and FIRA annual international robot soccer competitions. Hiroaki Kitano has formulated the International RoboCup Federation challenge: "In 2050 a team of fully autonomous humanoid robot soccer players shall win the soccer game, comply with the official rule of the FIFA, against the winner of the most recent World Cup."[145]

A lesser known challenge to promote AI research is the annual Arimaa challenge match. The challenge offers a $10,000 prize until the year 2020 to develop a program that plays the board game Arimaa and defeats a group of selected human opponents.

[edit] Applications of artificial intelligence

[edit] Business

Banks use artificial intelligence systems to organize operations, invest in stocks, and manage properties. In August 2001, robots beat humans in a simulated financial trading competition (BBC News, 2001).[146] A medical clinic can use artificial intelligence systems to organize bed schedules, make a staff rotation, and provide medical information. Many practical applications are dependent on artificial neural networks, networks that pattern their organization in mimicry of a brain's neurons, which have been found to excel in pattern recognition. Financial institutions have long used such systems to detect charges or claims outside of the norm, flagging these for human investigation. Neural networks are also being widely deployed in homeland security, speech and text recognition, medical diagnosis (such as in Concept Processing technology in EMR software), data mining, and e-mail spam filtering.

Robots have become common in many industries. They are often given jobs that are considered dangerous to humans. Robots have proven effective in jobs that are very repetitive which may lead to mistakes or accidents due to a lapse in concentration and other jobs which humans may find degrading. General Motors uses around 16,000 robots for tasks such as painting, welding, and assembly. Japan is the leader in using and producing robots in the world. In 1995, 700,000 robots were in use worldwide; over 500,000 of which were from Japan.[147]

[edit] Toys and games

The 1990s saw some of the first attempts to mass-produce domestically aimed types of basic Artificial Intelligence for education, or leisure. This prospered greatly with the Digital Revolution, and helped introduce people, especially children, to a life of dealing with various types of AI, specifically in the form of Tamagotchis and Giga Pets, the Internet (example: basic search engine interfaces are one simple form), and the first widely released robot, Furby. A mere year later an improved type of domestic robot was released in the form of Aibo, a robotic dog with intelligent features and autonomy.

[edit] List of applications

Typical problems to which AI methods are applied
  1. REDIRECT Template:Multicol
  1. REDIRECT Template:Multicol-break
  1. REDIRECT Template:Multicol-end
Other fields in which AI methods are implemented
  1. REDIRECT Template:Multicol
  1. REDIRECT Template:Multicol-break
  1. REDIRECT Template:Multicol-end
Lists of researchers, projects & publications

[edit] See also

Main list: List of basic artificial intelligence topics

[edit] Notes

  1. ^ Textbooks that define AI this way include Template:Harvnb, Template:Harvnb, and Template:Harvnb (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. ^ Although there is some controversy on this point (see Template:Harvnb), McCarthy states unequivocally "I came up with the term" in a c|net interview. (See Getting Machines to Think Like Us.)
  3. ^ See John McCarthy, What is Artificial Intelligence?
  4. ↑ a b Template:Harvnb
  5. ^ Template:Harvnb
  6. ↑ a b This list of intelligent traits is based on the topics covered by the major AI textbooks, including: Template:Harvnb, Template:Harvnb, Template:Harvnb and Template:Harvnb.
  7. ↑ a b General intelligence (strong AI) is discussed by popular introductions to AI, such as: Template:Harvnb, Template:Harvnb, Template:Harvnb
  8. ^ Template:Harvnb
  9. ^ See AI Topics: applications
  10. ^ PREFACE TO THE REVISED EDITION, Project Gutenberg eBook Erewhon, by Samuel Butler. Release Date: March 20, 2005.
  11. ^ Template:Harvnb