Near Optimal Learning Rate BP Algorithm and its Application in Traffic Forecast

Abstract:

Article Preview

Aimed at the inadequacy of the standard BP algorithm, a near optimal learning rate BP algorithm (NOLRBP) is presented. Selecting the learning rate of the algorithm based on one-dimensional search algorithm of optimization theory avoids the blindness in determining the learning rate. Simulations show that the algorithm is superior to the standard BP algorithm (SDBP), momentum BP algorithm (MOBP) and variable learning rate BP algorithm (VLBP).

Info:

Periodical:

Edited by:

Dongye Sun, Wen-Pei Sung and Ran Chen

Pages:

4513-4517

DOI:

10.4028/www.scientific.net/AMM.121-126.4513

Citation:

L. M. Qin and H. T. Zhang, "Near Optimal Learning Rate BP Algorithm and its Application in Traffic Forecast", Applied Mechanics and Materials, Vols. 121-126, pp. 4513-4517, 2012

Online since:

October 2011

Export:

Price:

$35.00

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

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