Intelligent Systems: Architectures and Perspectives

TL;DR

This paper reviews various hybrid intelligent system architectures combining neural networks, fuzzy systems, probabilistic reasoning, and evolutionary computation, highlighting their design aspects and the need for a common framework.

Contribution

It introduces generic architectures for hybrid intelligent systems and discusses their design considerations and perspectives, addressing the lack of a unified framework.

Findings

Different hybrid architectures are systematically presented.

Design aspects and perspectives of hybrid systems are analyzed.

Conclusions on hybrid system integration are provided.

Abstract

The integration of different learning and adaptation techniques to overcome individual limitations and to achieve synergetic effects through the hybridization or fusion of these techniques has, in recent years, contributed to a large number of new intelligent system designs. Computational intelligence is an innovative framework for constructing intelligent hybrid architectures involving Neural Networks (NN), Fuzzy Inference Systems (FIS), Probabilistic Reasoning (PR) and derivative free optimization techniques such as Evolutionary Computation (EC). Most of these hybridization approaches, however, follow an ad hoc design methodology, justified by success in certain application domains. Due to the lack of a common framework it often remains difficult to compare the various hybrid systems conceptually and to evaluate their performance comparatively. This chapter introduces the different generic architectures for integrating intelligent systems. The designing aspects and perspectives of different hybrid archirectures like NN-FIS, EC-FIS, EC-NN, FIS-PR and NN-FIS-EC systems are presented. Some conclusions are also provided towards the end.