An Optimization Approach to Design of Generalized BSB Neural Associative Memories

摘要

This article is concerned with the synthesis of the optimally perform- ing GBSB (generalized brain-state-in-a-box) neural associative memory given a set of desired binary patterns to be stored as asymptotically sta- ble equilibrium points. Based on some known qualitative properties and newly oberved fundamental properties of the GBSB model, the synthe- sis problem is formulated as a constrained optimization problem.