Title :
A new local training rule for higher-order associative memories
Author :
Chang, Jyh-Yeong ; Liu, Wei-Hsien ; Lin, Jin-Kuan
Author_Institution :
Dept. of Control Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
fDate :
27 Jun-2 Jul 1994
Abstract :
Necessary and sufficient conditions are derived for the correlation matrix and thresholds of higher-order associative memories (HOAMs) that can guarantee the recall of all training patterns. A local training rule is presented; this rule iteratively trains the correlation matrix and thresholds so that the complete recall conditions are satisfied. A design algorithm is proposed that ensures each training pattern is stored with as large a basin of attraction as possible. Computer simulations that demonstrate the power of the proposed local training rule are reported
Keywords :
content-addressable storage; correlation methods; iterative methods; learning (artificial intelligence); matrix algebra; correlation matrix; higher-order associative memories; iterative method; local training rule; necessary condition; sufficient condition; thresholds; training patterns recall; Algorithm design and analysis; Associative memory; Computer errors; Computer simulation; Control engineering; Cost function; Iterative algorithms; Neural networks; Pattern recognition; Sufficient conditions;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374329
