On neural networks that design neural associative memories

被引:15
|
作者
Chan, HY
Zak, SH
机构
[1] School of Electrical and Computer Engineering, Purdue University, West Lafayette
来源
关键词
associative memory; brain-state-in-a-box (BSB) model; constrained optimization; dynamic systems; stability;
D O I
10.1109/72.557674
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The design problem of generalized brain-state-in-a-box (GBSB) type associative memories is formulated as a constrained optimization program, and ''designer'' neural net works for solving the program in real time are proposed, The stability of the designer networks is analyzed using Barbalat's lemma, The analyzed and synthesized neural associative memories do not require symmetric weight matrices, Two types of the GBSB-based associative memories are analyzed, one when the network trajectories are constrained to reside in the hypercube [-1,1](n) and the other type when the network trajectories are confined to stay in the hypercube [0,1](n). Numerical examples and simulations are presented to illustrate the results obtained.
引用
收藏
页码:360 / 372
页数:13
相关论文
共 50 条