Title :
Design of bidirectional associative memories based on the perceptron training technique
Author :
Salih, Ismail ; Smith, Stanley H. ; Liu, Derong
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Stevens Inst. of Technol., Hoboken, NJ, USA
Abstract :
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 specific example is considered
Keywords :
content-addressable storage; pattern recognition; perceptrons; recurrent neural nets; bidirectional associative memories; feedback neural networks; linear inequalities; pattern recognition; perceptron training technique; synthesis approach; Algorithm design and analysis; Associative memory; Equations; Magnesium compounds; Network synthesis; Neural networks; Neurofeedback; Neurons; Pattern recognition; Vectors;
Conference_Titel :
Circuits and Systems, 1999. ISCAS '99. Proceedings of the 1999 IEEE International Symposium on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-5471-0
DOI :
10.1109/ISCAS.1999.777582
