Synthesis approach for bidirectional associative memories based on the perceptron training algorithm

Bidirectional associative memories are being used extensively for solving a variety of problems related to pattern recognition. In the present paper, a new synthesis approach is developed for bidirectional associative memories using feedback neural networks. The synthesis problem of bidirectional associative memories is formulated as a set of linear inequalities which can be solved using the perceptron training algorithm. To demonstrate the applicability of the present results, a speci"c example is considered. 2000 Elsevier Science B.V. All rights reserved.

• Type: Journal
• Year: 2000
• Where: IJON
• Authors: Ismail Salih, Stanley H. Smith, Derong Liu
• Keywords: Bidirectional Associative Memories, Feedback Neural Networks, IJON 2000, Pattern Recognition