ABSTRACT
Computational intelligence plays a major role in developing successful intelligent control systems. Inspired by the human brain and its intelligence, artificial neural networks (ANNs) emerged as one of the most exciting paradigms. Artificial neural networks approach the problem in a different way. The idea is to take a large enough number of handwritten digits, known as training examples, and then devise a method that helps the ANN learn from those training examples. There are other models of artificial neural networks in which feedback loops are possible. These models are called recurrent neural networks. Techniques include artificial neural networks, fuzzy logic control, which mimics linguistic and reasoning functions, and evolutionary algorithms. The chapter attempts to show how ANNs fulfill the promise of providing model-free learning controllers for a class of nonlinear systems, in the sense that a structural or parameterized model of the system dynamics is not needed.
