Cs. Leung, ENCODING METHOD FOR BIDIRECTIONAL ASSOCIATIVE MEMORY USING PROJECTIONON CONVEX-SETS, IEEE transactions on neural networks, 4(5), 1993, pp. 879-881
The traditional encoding method of bidirectional associative memory (B
AM) suggested by Kosko is based on the correlation method with which t
he capacity is very small. The enhanced Householder encoding algorithm
(EHCA) presented here is developed on the basis of the Householder en
coding algorithm (HCA) and projection on convex sets (POCS). The capac
ity of BAM with HCA tends to the dimension of the pattern pairs. Unfor
tunately, in BAM with HCA there are two different interconnection matr
ices and hence BAM with HCA may not converge when the initial stimulus
is not one of the library patterns. In EHCA the two matrices found by
HCA are reduced into one matrix by POCS. Hence, the convergent proper
ty of BAM can be maintained. Simulation results show that the capacity
of BAM with EHCA is greatly improved.