首页 | 本学科首页   官方微博 | 高级检索  
     


Zero Cost Function Training Algorithms for Three-Layered Feedforward Neural Networks
Authors:Zhang Daiyuan
Abstract:In this paper, two theorems are proved for zero cost function (or precise I/O mapping) training algorithms about three-layered feedforward neural networks. Two training algorithms based on Moore-Penrose pseudoinverse (MPPI) matris together with corresponding structure design guidelines are also proposed.
Keywords:Zero cost function   Precise I/O mapping   Moore-Penrose pseudoinverse matrix   Structure design   Feedforward neural networks
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号