Artificial Intelligence, Computational Intelligence, SoftComputing, Natural Computation - what's the difference?

What's the difference between the terms Artificial Intelligence, Computational Intelligence, SoftComputing, Natural Computation, Machine Learning, etc.?

In principle there is not so much difference.

Computational Intelligence is integrating the fields of Artificial Neural Networks, Evolutionary Computation, and Fuzzy Logic. It is the term formed by IEEE (see www.ieee-cis.org).

SoftComputing is the collocation for the same fields as CI expanded with Probabilistic Reasoning, Swarm Intelligence, and partly Chaos Theory.

Natural Computation assembles mathematical methods, which are inspired by solution patterns from nature. Basically these are again Artificial Neural Networks, Evolutionary Approaches, Swarn Intelligence, etc.

Machine Learning is based on Artificial Neural Networks, Support Vector Machines, Classification and Regression Trees, and some more similar methods. Important is that the resulting mathematical models are build by training from example data instead of being constructed analytically. This means that they are example based or empirical mathematical models instead of analytical ones.

Data Mining is the art of retrieving knowledge from huge data sets. The mathematical basis are mainly Machine Learning methods.

Summing up we have a lot of different terms, which describe more or less the same core of mathematical solution strategies. The difference is more based on the background and context of the users than on the mathematical substance.

Only Artificial Intelligence is a somehow broader term. The methods mentioned here so far can be dedicated to the so called "soft" part of AI. The contrary "hard" part of AI consists of topics like experts systems, formal logics, etc. and is looking for scientifically neat solutions rather than solving problems pragmatically.

Unfortunatly the various definitions and terms in the field of AI are still not used homogeniously and consistently in literature. Nevertheless after long religious wars the consence could be found between the protagonists of weak AI (the "scruffies") and of hard AI (the "neats") that "real intelligent" systems are composed by soft and hard methods.

Last update on 2016-12-04 by Andreas Kuhn.

Go back