Guaranteed recall of all training pairs for bidirectional associative memory

Y F Wang; J R Cruz; J R Mulligan

doi:10.1109/72.97933

Guaranteed recall of all training pairs for bidirectional associative memory

IEEE Trans Neural Netw. 1991;2(6):559-67. doi: 10.1109/72.97933.

Authors

Y F Wang¹, J R Cruz, J R Mulligan

Affiliation

¹ Dept. of Electr. and Comput. Eng., California Univ., Irvine, CA.

PMID: 18282871
DOI: 10.1109/72.97933

Abstract

Necessary and sufficient conditions are derived for the weights of a generalized correlation matrix of a bidirectional associative memory (BAM) which guarantee the recall of all training pairs. A linear programming/multiple training (LP/MT) method that determines weights which satisfy the conditions when a solution is feasible is presented. The sequential multiple training (SMT) method is shown to yield integers for the weights, which are multiplicities of the training pairs. Computer simulation results, including capacity comparisons of BAM, LP/MT BAM, and SMT BAM, are presented.