Paper Title:
Efficient Associative Memory Based on a Nonlinear Function Constitution and Dynamic Synapses
  Abstract

Nonlinear function constitution and dynamic synapses, against spurious state for Hopfield neural network are proposed. The model of the dynamical connection weight and the updating scheme of the states of neurons are given. Nonlinear function constitution improves the conventional Hebbian learning rule with linear outer product method. Simulation results show that both nonlinear function constitution and dynamic synapses can effectively increase the ability of error tolerance; furthermore, associative memory of neural network with the new method can both enlarge attractive basin and increase storage capacity.

  Info
Periodical
Advanced Materials Research (Volumes 225-226)
Edited by
Helen Zhang, Gang Shen and David Jin
Pages
479-482
DOI
10.4028/www.scientific.net/AMR.225-226.479
Citation
M. Xia, Y. C. Zhang, X. L. Ye, "Efficient Associative Memory Based on a Nonlinear Function Constitution and Dynamic Synapses", Advanced Materials Research, Vols. 225-226, pp. 479-482, 2011
Online since
April 2011
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Thierry Baudin, Anne Laure Etter, Ph. Gerber, Amel Samet-Meziou, Richard Penelle, Cristian Rey
Abstract:The stored energy of two cold rolled IF-Ti steels is calculated using finite element method from an EBSD microstructure. Because the...
1291
Authors: Ming He, Xiao Ming Zhang, Yong Heng Wang
Chapter 2: Information Technologies and Information Processing Algorithms
Abstract:Energy saving becomes one of the most important design considerations in the WBAN applications, and the power consumption is required to be...
1176
Authors: Yan Xiang, Jing Yang, Hao Zhu, Ding Xiang Dong
Chapter 2: Information Technologies and Information Processing Algorithms
Abstract:Design patterns is a good method to solve software crisis and realize the software reuse. It is usually combined with the Unified Modeling...
936