一种基于误差变化率的自适应反向传播算法

Download: PDF (594 KB)
Export: BibTeX | EndNote (RIS)

Abstract In order to overcome slow convergence rate of the standard BP algorithm, this paper presents an adaptive backpropagation algorithm which can update learning rate and birr factor automatically based on dynamic training error rate of change. Simulation result of the XOR problem shows much faster convergence rate can be obtained by this algorithm.

Key words： Neural networks Adaptive backpropagation algorithm XOR problem

Received: 30 January 1997

PACS:

TN-052

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors


	Xie Keming
	Zhang Jianwei

Cite this article:

Xie Keming,Zhang Jianwei. AN ADAPTIVE BACKPROPAGATION ALGORITHM BASED ON ERROR RATE OF CHANGE[J]. , 1998, 20(4): 570-572 .

URL:

http://jeit.ie.ac.cn/EN/ OR http://jeit.ie.ac.cn/EN/Y1998/V20/I4/570

[1]	YU Xin, XU Zhijian, CHEN Zhaorong, XU Chenhua. Lagrange Neural Network for Nonsmooth Nonconvex Optimization Problems with Equality and Inequality Constrains[J]. JEIT, 2017, 39(8): 1950-1955.