Title :
Neural networks with higher-order nonlinearity
Author :
Tai, Heng-Ming ; Jong, Tai-Lang
Author_Institution :
Dept. of Electr. Eng., Tulsa Univ., OK
fDate :
9/15/1988 12:00:00 AM
Abstract :
Neural networks for associative memory based on the Hopfield relaxation model and matched filtering techniques with higher-order nonlinearity are proposed. These high-order models show dramatic improvement in memory storage capacity and error-correction capability in comparison to conventional binary autoassociative models
Keywords :
content-addressable storage; error correction; filtering and prediction theory; neural nets; Hopfield relaxation model; associative memory; error-correction capability; higher-order nonlinearity; matched filtering techniques; memory storage capacity; neural networks;
Journal_Title :
Electronics Letters
