An enhanced training algorithm for multilayer neural networks based on reference output of hidden layer

Li, Yan and Rad, A. B. and Wen, Peng (1999) An enhanced training algorithm for multilayer neural networks based on reference output of hidden layer. Neural Computing and Applications, 8. pp. 218-225. ISSN 0941-0643

Yan Rad Wen Enhanced Training Algorithm 1999.pdf

Download (73Kb) | Preview


In this paper, the authors propose a new training algorithm which does not only rely upon the training samples, but also depends upon the output of the hidden layer. We adjust both the connecting weights and outputs of the hidden layer based on Least Square Backpropagation (LSB) algorithm. A set of ‘required’ outputs of the hidden layer is added to the input sets through a feedback path to accelerate the convergence speed. The numerical simulation results have demonstrated that the algorithm is better than conventional BP, Quasi-Newton BFGS (an alternative to the conjugate gradient methods for fast optimisation) and LSB algorithms in terms of convergence speed and training error. The proposed method does not suffer from the drawback of the LSB algorithm, for which the training error cannot be further reduced after three iterations.

Statistics for USQ ePrint 25061
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Faculty/School / Institute/Centre: Historic - Faculty of Engineering and Surveying - Department of Electrical, Electronic and Computer Engineering
Date Deposited: 16 Jul 2014 07:22
Last Modified: 16 Jul 2014 07:22
Uncontrolled Keywords: backpropagation, BFGS quasi-Newton, conjugate gradient algorithm, least square, multilayer neural networks
Fields of Research : 08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080108 Neural, Evolutionary and Fuzzy Computation
Socio-Economic Objective: E Expanding Knowledge > 97 Expanding Knowledge > 970108 Expanding Knowledge in the Information and Computing Sciences

Actions (login required)

View Item Archive Repository Staff Only