A fast adaptive algorithm for Hopfield neural network
SICE 2003 ANNUAL CONFERENCE, VOLS 1-3(2003)
摘要
This paper presents a gradient-based algorithm to speed up the convergence of the Hopfield neural network. To archive this, we introduce an individual step size eta, which is adapted according to the gradient information. The algorithm is applied to some benchmark problems, extensive simulations are performed and its effectiveness is confirmed.
更多查看译文
关键词
Hopfield neural network,gradient-based,combinatorial optimization,traveling salesman problem
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络