辽宁石油化工大学学报 ›› 2013, Vol. 33 ›› Issue (4): 83-86.

• 计算机与自动化 • 上一篇    下一篇

基于迭代学习的BP神经网络权值训练算法

周小勇,翟春艳,李书臣* ,苏成利   

  1. 辽宁石油化工大学信息与控制工程学院,辽宁抚顺113001
  • 收稿日期:2013-01-09 出版日期:2013-12-25 发布日期:2017-07-14
  • 作者简介:周小勇(1986-),男,湖北襄阳市,在读硕士
  • 基金资助:
    辽宁省科技攻关项目(2011216011)。

 
Weight Training Algorithm of BP Neural Network Based on Iterative Learning

ZHOU Xiaoyong, ZHAI Chunyan, LI Shuchen*, SU Chengli   

  1. College of Information and Control Engineering, Liaoning Shihua University, Fushun Liaoning 113001, China
  • Received:2013-01-09 Published:2013-12-25 Online:2017-07-14

摘要: 针对传统BP算法存在收敛速度过慢、易陷入局部极小的问题,提出基于迭代学习的BP神经网络权
值修正算法。该算法将迭代学习的原理与神经网络相结合,同时采用本次训练误差和前一次的训练误差修正神经
网络权值,提高了网络训练速度。仿真结果验证了该算法的有效性。

关键词: 神经网络 , 梯度算法 , 迭代学习型算法 , 权值训练 , 收敛速度

Abstract:  

A weight training algorithm of neural network based on iterative learning was proposed for the shortcoming of traditional BP algorithm, such as slow convergence and easily trapped into local minimal. The algorithm combined the principle of iterative learning with neural network, and it made use of the current and the previous training error to correct the neural network weights. It improved the speed of neural network training. Simulation results show the effectiveness of the algorithm.

Key words: Neural network ,  Gradient algorithm ,  Iterative learning algorithm ,  Weight training , Convergence speed

引用本文

周小勇,翟春艳,李书臣,苏成利. 基于迭代学习的BP神经网络权值训练算法[J]. 辽宁石油化工大学学报, 2013, 33(4): 83-86.

ZHOU Xiaoyong, ZHAI Chunyan, LI Shuchen, SU Chengli.  

Weight Training Algorithm of BP Neural Network Based on Iterative Learning
[J]. Journal of Liaoning Petrochemical University, 2013, 33(4): 83-86.

使用本文

0
    /   /   推荐

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://journal.lnpu.edu.cn/CN/

               https://journal.lnpu.edu.cn/CN/Y2013/V33/I4/83