Computational intelligence

Computational intelligence is the ability to obtain near-optimal solutions to tasks that requires some type of intelligence. Usally is defined also as the ability of a computer to learn a specific task from data or experimental observation. Computational Intelligence was defined by For Bezdek (1994), “a system is called computationally intelligent if it deals with low-level data such as numerical data, if it has a pattern-recognition component and if it does not use knowledge as exact and complete as the Artificially Intelligent one”.

But generally, computational intelligence is a set of nature-inspired computational methodologies and approaches to address complex real-world problems to which mathematical or traditional modelling can be useless for a few reasons:

• the processes might be too complex for mathematical reasoning
• the processes might contain some uncertainties during the process
• the process might simply be stochastic in nature.
• many real-life problems cannot be translated into binary language (unique values of 0 and 1) for computers to process it

The methods used are close to the human’s way of reasoning, i.e. it uses non exact and non-complete knowledge, and it is able to produce control actions in an adaptive way. CI therefore uses a combination of 5 main complementary techniques:

• Fuzzy logic: which enables the computer to understand natural language
• Artificial neural networks which permits the system to learn experiential data by operating like the biological one
• Evolutionary computing which is based on the process of natural selection
• Learning theory
• Probabilistic methods which helps dealing with uncertainty imprecision.

Except those main principles, currently popular approaches include biologically inspired algorithms such as swarm intelligence and artificial immune systems, which can be seen as a part of evolutionary computation, image processing, data mining, natural language processing, and artificial intelligence,which tends to be confused with Computational Intelligence. But although both Computational Intelligence (CI) and Artificial Intelligence (AI) seek similar goals, there’s a clear distinction between them.

Computational Intelligence is thus a way of performing like human beings. Indeed, the characteristic of “intelligence” is usually attributed to humans. More recently, many products and items also claim to be “intelligent”, an attribute which is directly linked to the reasoning and decision making.

See also

Artificial Intelligence, Mathematical optimization

Material

• http://www.andata.at/en/answer/artificial-intelligence-computational-intelligence-softcomputing-natural-computation-whats-the-difference.html
• Worrell, James. Computational Learning Theory: 2014-2015. University of Oxford. Presentation page of CLT course. University of Oxford.

Papers

• Somers, Casal, Mark John, Jose C. (July 2009). Using Artificial Neural Networks to Model Nonlinearity. SAGE Journals. Retrieved 2015-10-31.

Books

• Engelbrecht, Andries (2007). Computational Intelligence: An Introduction. Wiley & Sons.
• Poole, David; Mackworth, Alan; Goebel, Randy Computational Intelligence: A Logical Approach. Oxford University Press.
• Kruse, Borgelt, Klawonn, Moewes, Steinbrecher, Held, (2013) Computational Intelligence: A Methodological Introduction. Springer
• De Jong, K. (2006). Evolutionary Computation:A Unified Approach. MIT Press.
• Palit , Popovic, Ajoy K., Dobrivoje (2006). Computational Intelligence in Time Series Forecasting : Theory and Engineering Applications. Springer Science & Business Media.