Paper Title:
Neural Networks Model for Optimization an Study on Isomorphism Discernment
  Abstract

An artificial neural network is composed of large number of simple processing elements by direct links named connections, the benefits of neural networks extend beyond the high computation rates by massive parallelism. Optimization problems could be transferred into a feedback network, the network interconnects the neurons with a feedback path. Graphs isomorphism discernment is one of the most important and difficult issues in graphs theory based structures design. To solve the problem, a Hopfield neural networks (HNN) model is presented in this paper. The solution of HNN is design as a permutation matrix of two graphs, and some operators are improved to prevent premature convergence. It is concluded that the algorithm presented here is efficient for large-scale graphs isomorphism problem and other NP-complete optimization issues.

  Info
Periodical
Advanced Materials Research (Volumes 156-157)
Edited by
Jingtao Han, Zhengyi Jiang and Sihai Jiao
Pages
492-495
DOI
10.4028/www.scientific.net/AMR.156-157.492
Citation
M. Zhang, N. B. Liao, C. Zhou, "Neural Networks Model for Optimization an Study on Isomorphism Discernment", Advanced Materials Research, Vols. 156-157, pp. 492-495, 2011
Online since
October 2010
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: Miao Zhang, Ning Bo Liao, Chen Zhou, Xi Tao
Abstract:When using graph theory to conduct intelligent design for kinematic structure enumeration, the isomorphism identification of graphs is an...
2182
Authors: Long Hao
Abstract:The graph isomorphism problem is to study the relationship between two graphs which seem to be different, but essentially identically. A...
417
Authors: Ai Min Hou, Chuan Fu Hu, Zhi Feng Hao
Chapter 5: Computing Methods and Algorithms, Automation and Information Technologies, CAD Applications
Abstract:A general depth-first backtracking algorithm for graph isomorphism with the vertex partition and refinement technique is presented in this...
1919