A maximum overlap neural network for pattern recognition
暂无分享,去创建一个
Abstract The problem of recognizing noisy patterns is trivially solved by identifying the key pattern which has the largest overlap with the input. We show that a procedure that does this can be implemented in a simple layered neural network. Recognition is free of spurious states, the network never reaches a state of total confusion. Processing time scales as log M, where M is the number of stored patterns.
[1] Ron Meir,et al. Storing and Retrieving Information in a Layered Spin System , 1986 .
[2] Sompolinsky,et al. Spin-glass models of neural networks. , 1985, Physical review. A, General physics.
[3] W. A. Little,et al. Analytic study of the memory storage capacity of a neural network , 1978 .