Computational Intelligence Group

Webster's New Collegiate Dictionary [3] defines intelligence as:

"The ability to learn or understand or to deal with new or trying situations
The skilled use of reason.
The ability to apply knowledge to manipulate one's environment or to think abstractly as measured by objective criteria (or tests)"

Eberhart [1] defines computational intelligence "as a methodology involving computing (whether with a computer or wetware) that exhibits an ability to learn and/or to deal with new situations, such that the system is perceived to possess one or more attributes of reason such as generalisation, discovery, association and abstraction".

Computational intelligence or soft computing, is a research discipline which encompasses the theoretical formalization and applications of

Artificial Neural Networks (ANNs), also known as connection networks.

Evolutionary algorithms comprising Genetic Algorithms (GAs), Evolutionary Strategies (ES), Genetic Programming (GP), and Grammatical Evolution (GE).

Fuzzy Logic.

The design of intelligent and adaptive systems has been a perceptual goal of scientists and engineers. Many of the efforts engaged in realising this goal fall under the umbrella term of artificial intelligence (AI). Traditional or cartesian AI is founded on theories borrowed from cognitive psychology, linguistics and logic. The resultant systems are disembodied and symbolic, and are composed of two distinct elements:

A set of facts about the world
An inference mechanism or rules, for manipulation of these facts

Although advanced working systems have been implemented based on the cartesian AI paradigm, the motivation for further research along these lines has been dampened by a strong lack of connection with human intelligence, particularly the accepted failure of cartesian AI in the area of the sensory-motor loop. Behaviour oriented AI is a new field in the AI domain, whose theories are based on ethology, ecology, psychology and sociology. Cognition is perceived as a function of the nervous system as opposed to a function of logic. Emphasis is placed on a group or population of processing modules as opposed to an individual one. Emergent intelligence is derived based on Turning's principle of local interactions giving rise to global order.

It is hoped that adaptive and intelligent agents can be derived using methodologies and paradigms from the field of computational intelligence. The use of Computational Intelligence that links the complementary fields of neural networks, evolutionary algorithms and adaptive fuzzy systems is appropriate when systems that are analogous to the behavioural characteristic of biological systems are desired [2].

References

[1] Eberhart, R. C. Computational Intelligence: a Snapshot. In (Palaniswami, Attikiouzel, Marks II, Fogel and Fukuda Eds.) Computational Intelligence - A Dynamic System Perspective, pages 9-15. IEEE Press. 1995.

[2] Palaniswami, M., Attikiouzel, Y., Marks II, R., Fogel D. and Fukuda, T. Introduction. In (Palaniswami, Attikiouzel, Marks II, Fogel and Fukuda Eds.) Computational Intelligence - A Dynamic System Perspective, pages 1-5. IEEE Press. 1995.

[3] Webster's New Collegiate Dictionary. G. and C. Merriam Company. 1975.