Non-energy based neural networks for job-shop scheduling

被引：2

作者：

Jeng, MD

Chang, CY

机构：

[1] Department of Electrical Engineering, National Taiwan Ocean University

来源：

ELECTRONICS LETTERS | 1997年 / 33卷 / 05期

关键词：

neural networks; scheduling;

D O I：

10.1049/el:19970269

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A synchronous neural network architecture that implements a heuristic rule is proposed for solving the job-shop scheduling problem. The proposed rule can obtain better near-optimal solutions than some commonly used heuristic rules. The approach resolves drawbacks in prior work based on energy Functions such as invalid solutions, local minima and sensitivity to initial inputs.

引用

页码：399 / 400

页数：2