Neural networks and fuzzy logic in intelligent control

An introduction to fuzzy controllers and neural network controllers is presented, and methods for merging their capabilities to design hybrid neurofuzzy controllers (NFCs) are discussed. NFCs provide the knowledge representation power of fuzzy controllers and the learning capabilities of artificial neural networks. Several examples are given to contrast the architecture of the NFCs with individual fuzzy controllers or neural network controllers. The major elements of neurocontrol, a term used to refer to the neural networks that serve as controllers, are reviewed, with special emphasis on the learning behavior of these networks. Recent research on integrating neural networks with fuzzy logic control is outlined. It is shown that both of these techniques can use interpolative reasoning, which enables them to go beyond the traditional true-false restriction of the artificial intelligence symbolic methods.<
>