基于LASSO的神经网络权值阈值优化方法

数学理论与应用 ›› 2017, Vol. 37 ›› Issue (1): 61-66.

基于LASSO的神经网络权值阈值优化方法

霍剑光¹, 任贵政² ,杨扬¹

1.长沙理工大学数学与统计学院,长沙,410114; 2.长沙理工大学交通运输工程学院,长沙,410114

出版日期:2017-03-30 发布日期:2020-09-24

Neural Network Weight-Threshold Optimization Method Based on LASSO

Huo Jianguang¹, Ren Guizheng², Yang yang1

1.School of Mathematics and Computer Science,Changsha University of Science and Technology,Changsha 410114,China;
2.School of Traffic and Transportation Engineering,Changsha University of Science and Technology,Changsha 410114,China

Online:2017-03-30 Published:2020-09-24

摘要/Abstract

摘要： 本文在LASSO方法和神经网络误差回传思想的基础上,建立LASSO-BP算法.与BP神经网络算法和RBF径向基网络算法比较,该算法具有耗时短,抗干扰能力强的优点以及更好的分类效果.最终我们通过数值实验对该算法进行了验证.

关键词: LASSO方法, BP神经网络, RBF神经网络, 权值阈值

Abstract:

Based on the LASSO method and neural network,we establish a LASSO-BP algorithm.Compared with the BP neural network algorithm and the RBF algorithm,it has the advantages of time-consuming, strong anti-interference ability and better effects on classification.Its effectiveness is verified by numerical experiments.

Key words: LASSO method, BP neural network, RBF neural network, Weight and threshold

霍剑光, 任贵政 , 杨扬. 基于LASSO的神经网络权值阈值优化方法[J]. 数学理论与应用, 2017, 37(1): 61-66.

Huo Jianguang, Ren Guizheng, Yang yang.

Neural Network Weight-Threshold Optimization Method Based on LASSO [J]. Mathematical Theory and Applications, 2017, 37(1): 61-66.