GA优化神经网络思想  

Idea of GA Optimization of Neural Network

作　　者：李亚斐[1] 邹宽城[1] 李延会[1] 

机构地区：[1]长春工业大学计算机科学与工程学院,吉林长春130012

出　　处：《软件导刊》2009年第10期56-58,共3页Software Guide

摘　　要：概述了神经网络的概念、神经网络的基本元素和BP算法的基本原理,同时在BP算法的基础上用遗传算法来优化BP算法的权值,并且改变了BP算法的传播方向。Modern Living in neural networks has been widely used, neural networks are the most widely used BP algorithm, BP algorithm has the advantage of easy and plastic, but the BP algorithm is gradient-based method, which slow the convergence rate, and often by local minima problem, the general BP algorithm using GA optimization. This article provides an overview of the concept of neural networks, neural network and the basic elements of the basic.principles of BP algorithm, while at BP algorithm based on the use of genetic algorithm to optimize the weights of BP algorithm and BP algorithm changes the propagation direction.

关 键 词：神经网络 BP算法 GA 

分 类 号：TP389.1[自动化与计算机技术—计算机系统结构]