Second-order neural nets for constrained optimization.
作者信息
Zhang S, Zhu X, Zou L H
机构信息
Exper Vision Inc., San Jose, CA.
出版信息
IEEE Trans Neural Netw. 1992;3(6):1021-4. doi: 10.1109/72.165605.
PMID:18276500
Abstract
Analog neural nets for constrained optimization are proposed as an analogue of Newton's algorithm in numerical analysis. The neural model is globally stable and can converge to the constrained stationary points. Nonlinear neurons are introduced into the net, making it possible to solve optimization problems where the variables take discrete values, i.e., combinatorial optimization.
摘要
Zotero 插件