Paper Title:
An Improved BP Algorithm Based on Steepness Factor and Adaptive Learning Rate Adjustment Factor
  Abstract

BP network is the most widely used of the neural net work model, but there are many problems of slow convergence speed and easily getting into the local minimum in the conventional BP algorithm. For this, an improved algorithm is proposed. Momentum term is added, steepness factors are introduced and adaptive learning rate adjustment factor is added. In the Matlab platform simulations are carried out by each improvement methods on the same BP neural network. The results show that: Convergence of improved BP network is decreased from 1000 to 49 and the error is decreased from 10-2 to 10-6. The convergence speed has been significantly improved and the error has been decreased. Using the synthesis improvement method effect is obvious and it provides a good theoretical basis for the practical application.

  Info
Periodical
Chapter
Chapter 2: Advanced Design Science (1)
Edited by
Dongye Sun, Wen-Pei Sung and Ran Chen
Pages
705-709
DOI
10.4028/www.scientific.net/AMM.121-126.705
Citation
X. H. Zhang, F. J. Ren, Y. C. Jiang, "An Improved BP Algorithm Based on Steepness Factor and Adaptive Learning Rate Adjustment Factor", Applied Mechanics and Materials, Vols. 121-126, pp. 705-709, 2012
Online since
October 2011
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Tian Pei Zhou, Wen Fang Huang
Abstract:In the process of recycling chemical product in coking object, ammonia and tar were indispensable both metallurgy and agriculture, so the...
1945
Authors: Wei Feng Wang, Jun Tao Yuan, An Lin Zhang, Meng Li
Chapter 5: Road and Bridge Engineering
Abstract:For present-day bridges.cable tensions test is a vitally important job in course of construction.The tensions condition of cables plays an...
1117
Authors: Hui Qin Sun, Zhi Hong Xue, Ke Jun Sun, Su Zhi Wang, Yun Du
Chapter 2: Manufacturing Technology
Abstract:BP neural network is currently the most widely used of neural network models in practical application in transformer fault diagnosis. BP...
789
Authors: Jian Xue Chen, Shui Yu
Chapter 4: Mechatronics and Automation Manufacturing Systems, Control Technologies
Abstract:Combining ant colony optimization (ACO) algorithm with back-propagation (BP) algorithm, the ACO-BP algorithm is proposed to optimize shift...
553
Authors: Teng Li, Xiao Mei Yuan, Shi Liang Yang, Xin Hui Zhang
Chapter 2: Motivation, Thermal, Electronics and Power Engineering
Abstract:A new approach is presented for analyzing gas mixtures by transforming the problem into a pattern classification one to reduce the effect of...
548