A Four Color Problem Solver using a discontinuous time Neural Network

• YAMAMOTO Takao

  Nippon Institute of Technology

• JIN'NO Kenya

  Nippon Institute of Technology

• HIROSE Haruo

  Nippon Institute of Technology

Bibliographic Information

Other Title

• 離散時間型ニューラルネットによる4色問題の解法

Abstract

This article considers the Four Color Problem solver using a neural network. There is a combinatorial optimization problems solver with a neural network proposed by Tank and Hopfield. This network has monodecreasing energy function correspond a minimum of cost function. This network can find solution of the problems in a few cases, because local minimums exist in energy function. In this article, we propose a network without such energy function and local minimum. And this system guarantees a fixed point corresponds to a minimum of cost function.

Journal

• IEICE technical report. Nonlinear problems

  IEICE technical report. Nonlinear problems 99 (323), 109-114, 1999-09-21

  The Institute of Electronics, Information and Communication Engineers

Keywords

• Neural Networks
• Combinatorial Optimization Problems
• Energy
• Local minimum
• Four Color Problem

Details

• CRID: 1572824502200466816
• NII Article ID: 110003292814
• NII Book ID: AN10060800
• Text Lang: ja
• Data Source:
  • CiNii Articles