Misplaced Pages

Artificial intelligence

Article snapshot taken from Wikipedia with creative commons attribution-sharealike license. Give it a read and then ask your questions in the chat. We can research this topic together.

This is an old revision of this page, as edited by 69.22.218.97 (talk) at 14:35, 5 June 2005. The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

Revision as of 14:35, 5 June 2005 by 69.22.218.97 (talk)(diff) ← Previous revision | Latest revision (diff) | Newer revision → (diff)

Artificial intelligence (also known as artificial idiot or machine intelligence and often abbreviated as AI) is intelligence exhibited by any manufactured (i.e. artificial) system. The term is often applied to general purpose computers and also in the field of scientific investigation into the theory and practical application of AI.

Modern AI research is concerned with producing useful machines to automate human tasks requiring intelligient behavior. Examples include scheduling resources such as military units, answering questions about products for customers, understanding and transcibing speech, and recognizing faces in CCTV cameras. As such, it has become an engineering discipline, focussed on providing solutions to practical problems. AI methods were used to schedule units in the first Gulf War, and the costs saved by this efficiency have repaid the US government's entire investment in AI research since the 1950s. AI systems are now in routine use in many businesses, hospitals and military units around the world, as well as built into common home computer software such as Microsoft Office and video games. ( See Raj Reddy's AAAI paper for a huge review of real-world AI systems in deployment today.)

AI methods are often employed in cognitive science research, which explicitly tries to model subsystems of human cognition. (This is in contrast to AI research proper, which seeks to build useful machines, not to model humans.)

Historically, AI researchers aimed for the loftier goal of so-called strong AI, of simulating complete, human-like intelligence. This goal is epitomised by the fictional strong AI computer HAL in the film 2001: A Space Odyssey. This goal is unlikely to be met in the near future and is no longer the subject of serious AI research. The label "AI" has something of a bad name due to the failure of these early expectations, and aggravation by various popular science writers and media personalities such as Professor Kevin Warwick whose work has raised the expectations of AI research far beyond its current capabilities. For this reason, many AI researchers say they work in cognitive science, informatics, statistical inference or information engineering in an an attempt to distance themselves from such charlatanism.

AI has seen many research paradigms, including symbolic, connectionist and Bayesian approaches. There is still no consensus as to the best way to proceed. Recent fashionable research areas Bayesian Networks and Artificial Life.

Sub-fields of AI research

GOFAI - 'Good Old Fashioned AI'

Connectionism

Artificial Life and Evolution

Bayesian Methods and Learning

Fuzzy Systems

History

Development of AI theory

Much of the (original) focus of artificial intelligence research draws from an experimental approach to psychology, and emphasizes what may be called linguistic intelligence (best exemplified in the Turing test).

Approaches to artificial intelligence that do not focus on linguistic intelligence include robotics and collective intelligence approaches, which focus on active manipulation of an environment, or consensus decision making, and draw from biology and political science when seeking models of how "intelligent" behavior is organized.

Artificial intelligence theory also draws from animal studies, in particular with insects, which are easier to emulate as robots (see artificial life), as well as animals with more complex cognition, including apes, who resemble humans in many ways but have less developed capacities for planning and cognition. AI researchers argue that animals, which are simpler than humans, ought to be considerably easier to mimic. But satisfactory computational models for animal intelligence are not available.

Seminal papers advancing the concept of machine intelligence include A Logical Calculus of the Ideas Immanent in Nervous Activity (1943), by Warren McCulloch and Walter Pitts, and On Computing Machinery and Intelligence (1950), by Alan Turing, and Man-Computer Symbiosis by J.C.R. Licklider. See cybernetics and Turing test for further discussion.

There were also early papers which denied the possibility of machine intelligence on logical or philosophical grounds such as Minds, Machines and Gödel (1961) by John Lucas .

With the development of practical techniques based on AI research, advocates of AI have argued that opponents of AI have repeatedly changed their position on tasks such as computer chess or speech recognition that were previously regarded as "intelligent" in order to deny the accomplishments of AI. They point out that this moving of the goalposts effectively defines "intelligence" as "whatever humans can do that machines cannot".

John von Neumann (quoted by E.T. Jaynes) anticipated this in 1948 by saying, in response to a comment at a lecture that it was impossible for a machine to think: "You insist that there is something a machine cannot do. If you will tell me precisely what it is that a machine cannot do, then I can always make a machine which will do just that!". Von Neumann was presumably alluding to the Church-Turing thesis which states that any effective procedure can be simulated by a (generalized) computer.

In 1969 McCarthy and Hayes started the discussion about the frame problem with their essay, "Some Philosophical Problems from the Standpoint of Artificial Intelligence".

Experimental AI research

Artificial intelligence began as an experimental field in the 1950s with such pioneers as Allen Newell and Herbert Simon, who founded the first artificial intelligence laboratory at Carnegie Mellon University, and McCarthy and Marvin Minsky, who founded the MIT AI Lab in 1959. They all attended the aforementioned Dartmouth College summer AI conference in 1956, which was organized by McCarthy, Minsky, Nathan Rochester of IBM and Claude Shannon.

Historically, there are two broad styles of AI research - the "neats" and "scruffies". "Neat", classical or symbolic AI research, in general, involves symbolic manipulation of abstract concepts, and is the methodology used in most expert systems. Parallel to this are the "scruffy", or "connectionist", approaches, of which artificial neural networks are the best-known example, which try to "evolve" intelligence through building systems and then improving them through some automatic process rather than systematically designing something to complete the task. Both approaches appeared very early in AI history. Throughout the 1960s and 1970s scruffy approaches were pushed to the background, but interest was regained in the 1980s when the limitations of the "neat" approaches of the time became clearer. However, it has become clear that contemporary methods using both broad approaches have severe limitations.

Artificial intelligence research was very heavily funded in the 1980s by the Defense Advanced Research Projects Agency in the United States and by the fifth generation computer systems project in Japan. The failure of the work funded at the time to produce immediate results, despite the grandiose promises of some AI practitioners, led to correspondingly large cutbacks in funding by government agencies in the late 1980s, leading to a general downturn in activity in the field known as AI winter. Over the following decade, many AI researchers moved into related areas with more modest goals such as machine learning, robotics, and computer vision, though research in pure AI continued at reduced levels.

Modern AI

Modern AI research focusses on practical engineering tasks. (Supporters of Strong AI may call this approach 'weak AI').

There are several fields of AI, one of which is natural language. Many weak AI fields have specialised software or programming languages created for them. For example, the 'most-human' natural language chatterbot A.L.I.C.E. uses a programming language AIML that is specific to its program, and the various clones, named Alicebots. Jabberwacky is a little closer to strong AI, since it learns how to converse from the ground up based solely on user interactions.

When viewed with a moderate dose of cynicism, AI can be viewed as ‘the set of computer science problems without good solutions at this point.’ Once a sub-discipline results in useful work, it is carved out of artificial intelligence and given its own name. Examples of this are pattern recognition, image processing, neural networks, natural language processing, robotics and game theory. While the roots of each of these disciplines is firmly established as having been part of artificial intelligence, they are now thought of as somewhat separate.

Whilst progress towards the ultimate goal of human-like intelligence has been slow, many spinoffs have come in the process. Notable examples include the languages LISP and Prolog, which were invented for AI research but are now used for non-AI tasks. Hacker culture first sprang from AI laboratories, in particular the MIT AI Lab, home at various times to such luminaries as McCarthy, Minsky, Seymour Papert (who developed Logo there), Terry Winograd (who abandoned AI after developing SHRDLU).

Many other useful systems have been built using technologies that at least once were active areas of AI research. Some examples include:

The vision of artificial intelligence replacing human professional judgment has arisen many times in the history of the field, and today in some specialized areas where "expert systems" are routinely used to augment or to replace professional judgment in some areas of engineering and of medicine. An example of an expert system is Clippy the paperclip in Microsoft Office which tried to predict what advice the user would like.

Micro-World AI

The real world is full of distracting and obscuring detail: generally science progresses by focussing on artificially simple models of reality (in physics, frictionless planes and perfectly rigid bodies, for example). In 1970 Marvin Minsky and Seymour Papert, of the MIT AI Laboratory, proposed that AI research should likewise focus on developing programs capable of intelligent behaviour in artificially simple situations known as micro-worlds. Much research has focussed on the so-called blocks world, which consists of coloured blocks of various shapes and sizes arrayed on a flat surface. Micro-World AI


Applications

Languages, Programming Style and Software Culture

GOFAI research is often done in Lisp or Prolog. Bayesian work often uses Matlab or Lush (a numerical dialect of Lisp). These languages include many specialist probabalistic libraries. Real-life and especially real-time systems are likely to use C++. AI programmers are often academics and emphasise rapid development and prototying rather than bulletproof software engineering practices. Hence the use of interpreted languages to empower rapid command-line testing and experimentation. AI culture is historically tied to Unix and hacker cultures, as they share a common birthplace at MIT.

AI in the UK

AI research is carried out all over the world. In the UK, the most noted universities are Edinburgh and Sussex although AI research activities can be found in most universities in the country. Since the publication of the Lighthill report UK funding for "AI" dried up, though UK research continues under more politically-acceptable headings such as "Informatics", "Information Engineering" and "Inference". Microsoft runs a large AI research group in Cambridge which works closely with the university. HP labs in Bristol, BT in Ipswitch, and various government defence agencies also research AI applications.

AI in Business

According to Haag, Cummings, etc.(2004) there are four common techniques of Artificial Intelligence used in businesses:

  • Expert Systems
  • Neural Networks
  • Genetic Algorithms
  • Intelligent Agents

Expert Systems apply reasoning capabilities to reach a conclusion. An expert system can process large amounts of known information and provide conclusions based on them.

Neural Networks are AI that are capable of finding and differentiating between patterns. Police Departments use neural networks to identify corruption.

Genetic Algorithms are designed to apply the survival of the fittest process to generate increasingly better solutions to the problem. Investment brokers use Genetic Algorithms to create the best possible combination of investment opportunities for their clients.

An Intelligence Agent is software that assists you, or acts on your behalf, in performing repetitive computer-related tasks. Examples of its uses are data mining programs and monitoring and surveillance agents.


Logic programming was sometimes considered a field of artificial intelligence, but this is no longer the case.

Machines Displaying Some Degree of Intelligence

There are many examples of programs displaying some degree of intelligence. Some of these are:

  • Twenty Questions - A neural-net based game of 20 questions
  • The Start Project - a web-based system which answers questions in English.
  • Brainboost - another question-answering system
  • Cyc, a knowledge base with vast collection of facts about the real world and logical reasoning ability.
  • Jabberwacky, a learning chatterbot
  • ALICE, a chatterbot
  • Alan, another chatterbot
  • Albert One, multi-faceted chatterbot
  • ELIZA, a program which pretends to be a psychotherapist, developed in 1966
  • PAM (Plan Applier Mechanism) - a story understanding system developed by John Wilensky in 1978.
  • SAM (Script applier mechanism) - a story understanding system, developed in 1975.
  • SHRDLU - an early natural language understanding computer program developed in 1968-1970.
  • Creatures, a computer game with breeding, evolving creatures coded from the genetic level upwards using a sophisticated biochemistry and neural network brains.
  • BBC news story on the creator of Creatures latest creation. Steve Grand's Lucy.
  • AARON - artificial intelligence, which creates its own original paintings, developed by Harold Cohen.
  • Eurisko - a language for solving problems which consists of heuristics, including heuristics for how to use and change its heuristics. Developed in 1978 by Douglas Lenat.
  • X-Ray Vision for Surgeons - a group in MIT which researches medical vision.
  • Neural networks-based programs for backgammon and go.
  • Talk to William Shakespeare - William Shakespeare chatbot

AI Researchers

There are many thousands of AI researchers (see Category:Artificial intelligence researchers) around the world at hundreds of research institutions and companies. Among the many who have made significant contributions are:

Further reading

Non-fiction

See also Important publications in artificial intelligence.

Sources

  • John McCarthy: Proposal for the Dartmouth Summer Research Project On Artificial Intelligence.
  • John Searle: Minds, Brains and Programs Behavioral and Brain Sciences 3 (3): 417-457 1980. ]

See also

Philosophy

Logic

Science

Applications

Uncategorised

  • Collective intelligence - the idea that a relatively large number of people co-operating in one process can lead to reliable action.

in time of the emergence of smarter-than-human intelligence.

External links

General

AI related organizations

Categories: