文件名称:The-Systematic-Trajectory-Search-Algorithm-for-Fe
介绍说明--下载内容均来自于网络,请自行研究使用
In this paper we present the systematic trajectory search
algorithm (STSA) which first globally explores the solution
space then makes thorough local searches in promising areas.
The STSA has been tested on training feedforward neural
networks to solve the n-bit parity problem of various sizes
and two real medical diagnosis problems. The experimental
results show that the feedforward neural networks trained by
the proposed algorithm have very good classification ability.
algorithm (STSA) which first globally explores the solution
space then makes thorough local searches in promising areas.
The STSA has been tested on training feedforward neural
networks to solve the n-bit parity problem of various sizes
and two real medical diagnosis problems. The experimental
results show that the feedforward neural networks trained by
the proposed algorithm have very good classification ability.
(系统自动生成,下载前可以参看下载内容)
下载文件列表
The Systematic Trajectory Search Algorithm for Feedforward Neural Network Training.pdf