Title :
Design of Hopfield content-addressable memories
Author :
Xinhua Zhuang ; Yan Huang ; Yu, Frank A.
Author_Institution :
Dept. of Electr. & Comput. Eng., Missouri Univ., Columbia, MO, USA
fDate :
2/1/1994 12:00:00 AM
Abstract :
The Hamming-stability perceptron learning rule (PHSL) is proposed for the Hopfield content-addressable memories based on three well recognized criteria, which amount to widely expanding the basin of attraction around each desired attractor. Extensive experiments convincingly show that the PHSL does take good care of three optimal criteria
Keywords :
Hopfield neural nets; content-addressable storage; learning (artificial intelligence); stability; Hamming-stability perceptron learning rule; Hopfield content-addressable memories; experiments; Associative memory; CADCAM; Computer aided manufacturing; Content addressable storage; Logic; Neural networks; Neurons; Performance analysis; Stability; Symmetric matrices;
Journal_Title :
Signal Processing, IEEE Transactions on