Eigenvalue problem approach to discrete minimization

被引:0
|
作者
Litinskii, LB [1 ]
机构
[1] Russian Acad Sci, Inst Opt Neural Technol, Moscow, Russia
来源
ARTIFICIAL NEURAL NETWORKS: FORMAL MODELS AND THEIR APPLICATIONS - ICANN 2005, PT 2, PROCEEDINGS | 2005年 / 3697卷
关键词
NEURAL-NETWORKS; OPTIMIZATION;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The problem of finding of the deepest local minimum of a quadratic functional of binary variables is discussed. Our approach is based on the asynchronous neural dynamics and utilizes the eigenvalues and eigenvectors of the connection matrix. We discuss the role of the largest eigenvalues. We report the results of intensive computer experiments with random matrices of large dimensions N similar to 10(2) - 10(3).
引用
收藏
页码:405 / 410
页数:6
相关论文
共 50 条