Associative memory for intelligent control

In many industrial applications of softcomputing, intelligent controls are important to accomplish high level tasks. Intelligent controls, however, ne ed specific knowledge for each task. Therefore developing good memory is cr ucial to store the required knowledge efficiently and robustly. Neural netw ork associative memories are the most suitable for the role because of thei r flexibility and content addressability. In this paper, first, we describe the basic concept of the neural network associative memories and the conve ntional learning algorithms. After pointing out some problems of the associ ative memories, we explain a novel learning algorithm, which is superior to the conventional. ones. Finally, we introduce an associative memory suited for the intelligent controls and show the effectiveness by a number of com puter simulations. (C) 2000 IMACS/Elsevier Science B.V. All rights reserved .