07-09-2012, 10:55 AM
ARTIFICIAL INTELLIGENCE
ARTIFICI[2].DOC (Size: 842.18 KB / Downloads: 37)
INTRODUCTION
Artificial Intelligence (AI), the study of how to make computers do things that minds can do. These include many things not normally thought of as intelligent, such as moving without bumping into obstacles, or gaining information about an environment through vision.
Humans share these capacities, and also the ability to learn from experience, with many other animals. Only humans, however, have language. The intellectual aspects of intelligence depend on language.
Much work in AI models intellectual tasks, as opposed to the sensory, motor, and adaptive abilities possessed by all mammals. Most AI systems are programs, existing only inside the computer. Others are robots, controlled either by a program or (in “situated” robots) by engineered reflexes.
There are three types of AI:
1 Symbolic
2 connectionist AI
3 evolutionary
Each has characteristic strengths and weaknesses.
Symbolic AI
Symbolic AI is based in logic. It uses sequences of rules to tell the computer what to do next. Expert systems consist of many so-called IF-THEN rules: IF this is the case, THEN do those. Since both sides of the rule can be defined in complex ways, rule-based programs can be very powerful.
The performance of a logic-based program need not appear “logical”, since some rules may cause it to take apparently irrational actions. “Illogical” AI programs are not used for practical problem-solving, but are useful in modelling how humans think.
Symbolic programs are good at dealing with set problems, and at representing hierarchies (in grammar, for example, or planning). But they are brittle: if part of the expected input data is missing or mistaken, they may give a bad answer or no answer at all.
Connectionist AI
Connectionism is inspired by the brain. It is closely related to computational neuroscience, which models actual brain cells and neural circuits. Connectionist AI uses artificial neural networks made of many units working in parallel.
Each unit is connected to its neighbours by links that can raise or lower the likelihood that the neighbour unit will fire (excitatory and inhibitory connections respectively). Neural networks that are able to learn do so by changing the strengths of these links, depending on past experience. These simple units are much less complex than real neurons. Each can do only one thing: for instance, report a tiny vertical line at a particular
PURPOSES OF ARTIFICIAL INTELLIGENCE
AI developers have one or both of two motivations: technological and psychological. Some want to make their computers do a useful task, without caring just how they do it.
These may include methods that people cannot match, such as sensitivity to ultraviolet light, or an exhaustive search ahead through all the legal chess moves for several steps. Others want to learn about human minds (or brains). They see their programs as psychological theories, and avoid methods that humans cannot use.
Psychologists can be helped by AI because they must state their theories very clearly to express them as programs. If the program fails to produce the intended results, then the theory must be mistaken, but the computer run may indicate where the mistake is.
If the program succeeds, it does not follow that people think in the same way: only psychological (or neurophysiological) evidence can confirm that. AI is used by financial institutions, scientists and medical practitioners, design engineers, public transport schedulers, planning authorities, government departments, and security services, among many others.
AI techniques are also applied in systems used to browse the Internet and online news and wire services. In the home, AI systems can provide guidance on gardening, travel, car maintenance, and many other matters; and AI robots are being developed to assist the disabled.
ARTIFICI[2].DOC (Size: 842.18 KB / Downloads: 37)
INTRODUCTION
Artificial Intelligence (AI), the study of how to make computers do things that minds can do. These include many things not normally thought of as intelligent, such as moving without bumping into obstacles, or gaining information about an environment through vision.
Humans share these capacities, and also the ability to learn from experience, with many other animals. Only humans, however, have language. The intellectual aspects of intelligence depend on language.
Much work in AI models intellectual tasks, as opposed to the sensory, motor, and adaptive abilities possessed by all mammals. Most AI systems are programs, existing only inside the computer. Others are robots, controlled either by a program or (in “situated” robots) by engineered reflexes.
There are three types of AI:
1 Symbolic
2 connectionist AI
3 evolutionary
Each has characteristic strengths and weaknesses.
Symbolic AI
Symbolic AI is based in logic. It uses sequences of rules to tell the computer what to do next. Expert systems consist of many so-called IF-THEN rules: IF this is the case, THEN do those. Since both sides of the rule can be defined in complex ways, rule-based programs can be very powerful.
The performance of a logic-based program need not appear “logical”, since some rules may cause it to take apparently irrational actions. “Illogical” AI programs are not used for practical problem-solving, but are useful in modelling how humans think.
Symbolic programs are good at dealing with set problems, and at representing hierarchies (in grammar, for example, or planning). But they are brittle: if part of the expected input data is missing or mistaken, they may give a bad answer or no answer at all.
Connectionist AI
Connectionism is inspired by the brain. It is closely related to computational neuroscience, which models actual brain cells and neural circuits. Connectionist AI uses artificial neural networks made of many units working in parallel.
Each unit is connected to its neighbours by links that can raise or lower the likelihood that the neighbour unit will fire (excitatory and inhibitory connections respectively). Neural networks that are able to learn do so by changing the strengths of these links, depending on past experience. These simple units are much less complex than real neurons. Each can do only one thing: for instance, report a tiny vertical line at a particular
PURPOSES OF ARTIFICIAL INTELLIGENCE
AI developers have one or both of two motivations: technological and psychological. Some want to make their computers do a useful task, without caring just how they do it.
These may include methods that people cannot match, such as sensitivity to ultraviolet light, or an exhaustive search ahead through all the legal chess moves for several steps. Others want to learn about human minds (or brains). They see their programs as psychological theories, and avoid methods that humans cannot use.
Psychologists can be helped by AI because they must state their theories very clearly to express them as programs. If the program fails to produce the intended results, then the theory must be mistaken, but the computer run may indicate where the mistake is.
If the program succeeds, it does not follow that people think in the same way: only psychological (or neurophysiological) evidence can confirm that. AI is used by financial institutions, scientists and medical practitioners, design engineers, public transport schedulers, planning authorities, government departments, and security services, among many others.
AI techniques are also applied in systems used to browse the Internet and online news and wire services. In the home, AI systems can provide guidance on gardening, travel, car maintenance, and many other matters; and AI robots are being developed to assist the disabled.