STATE GENERATORS AND COMPLEX NEURAL MEMORIES

被引：5

作者：

KAK, SC

机构：

[1] Department of Electrical and Computer Engineering, Louisiana State University, Baton Rouge, 70803-5901, LA

来源：

PRAMANA-JOURNAL OF PHYSICS | 1992年 / 38卷 / 03期

关键词：

NEURAL NETWORKS; NONLINEAR SYSTEMS; ITERATED MAPS;

D O I：

10.1007/BF02875373

中图分类号：

O4 [物理学];

学科分类号：

0702 ;

摘要：

The mechanism of self-indexing for feedback neural networks that generates memories from short subsequences is generalized so that a single bit together with an appropriate update order suffices for each memory. This mechanism explains how stimulating an appropriate neuron can recall a memory. Although information is distributed in this model, yet our self-indexing mechanism makes it appear localized. Also a new complex valued neuron model is presented to generalize McCulloch-Pitts neurons.

引用

页码：271 / 278

页数：8

共 12 条

[1] INFORMATION-STORAGE IN NEURAL NETWORKS WITH LOW-LEVELS OF ACTIVITY [J].