摘要
BP神经网络算法是在BP神经网络现有算法的基础上提出的,是通过任意选定一组权值,将给定的目标输出直接作为线性方程的代数和来建立线性方程组,解得待求权,不存在传统方法的局部极小及收敛速度慢的问题,且更易理解。
The BP neural networks algorithm presented in this paper is based on the existing algorithm. The basic principle of the method is to calculate the weight by solving the linear equations after choosing a group of random weight, and the given object output is used as the algebraic sum of the linear equations to establish the linear equations set and further to get the weight required. There are no the problems of the traditional method such as the local minimum and the slower rate of convergence in BP neural networks algorithm, and this algorithm is easier to understand.
出处
《科技情报开发与经济》
2006年第3期241-242,共2页
Sci-Tech Information Development & Economy
基金
山西省自然科学基金项目(NO:200310048)论文
作者简介
鄢玉，女，1976年10月生，现为太原理工大学机械学院2003级在读硕士研究生，山西省太原市西矿街53号（太原理工大学西区），030024．
