| 摘要: |
| 基于联想记忆各记忆模式的吸引域之间应保持大小平衡的思想．提出了设计Hopfield联想记忆网络的极大极小准则，即设计出的对称连接权阵应使得网络最小的记忆模式吸引域达到最大．首先提出了一种快速学习算法;再发展了一个启发性迭代学习算法，称为约束感知器优化学习算法．大量实验结果表明了本文学习算法的优越性． |
| 关键词: 联想记忆,极大极小准则，快速学习算法，约束感知器优化学习算法． |
| DOI： |
| 分类号: |
| 基金项目:本文研究得到国家攀登计划和国家自然科学基金资助. |
|
| TWO LEARNING ALGORITHMS OF HOPFIELD ASSOCIATIVE MEMORY BASED ON MINIMAX CRITERION |
|
Liang Xuehin,Wu Lide
|
| Abstract: |
| Based on the idea that the domains of attraction of all memorizad patterns must possess balanced shape,a minimax criterion for design of HoFfield associative memo-ry，which requires the smallest domain of attraction to be maximized，is proposed in this paper．A quick learning algorithm is first given，and furtherly，a constrained perception optimization algorithm is developed．A large number of simulation results confirm advan-tages of these algorithms given in this paper over existing ones． |
| Key words: Associative memory,minimax criterion,quick learning algorithm,con-strained perception optimization algorithm． |
