Title :
Overlapping decompositions in the design of associative memories
Author :
Akar, Mehmet ; Sezer, M. Erol
Author_Institution :
Ohio State Univ., Columbus, OH, USA
Abstract :
This paper is concerned with the design of neural networks to be used as associative memories. The idea of overlapping decompositions, which is extensively used in the solution of large-scale problems as a method of reducing the computational work, is applied to discrete-time neural networks with binary neurons. It is shown that if the desired memory matrix accepts a suitable overlapping decomposition, then the problem can be solved by synthesizing a number of smaller networks independently. The concept is illustrated with two examples
Keywords :
Hopfield neural nets; associative processing; content-addressable storage; matrix algebra; pattern recognition; Hopfield neural nets; associative memory; binary neurons; discrete-time neural networks; memory matrix; overlapping decompositions; pattern recognition; Associative memory; Biological neural networks; Computer networks; Hopfield neural networks; Intelligent networks; Large-scale systems; Matrix decomposition; Network synthesis; Neural networks; Neurons;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.616203
