Please use this identifier to cite or link to this item:
Title: Backpropagation with two-phase magnified gradient function
Authors: Cheung, CC
Ng, SC
Keywords: Backpropagation
Gradient methods
Issue Date: 2008
Source: Neural Networks, 2008, IJCNN 2008, (IEEE World Congress on Computational Intelligence), IEEE International Joint Conference on : Hong Kong, China, 1-8 June 2008, p. 710-715 (CD) How to cite?
Abstract: Backpropagation (BP) learning algorithm is the most widely supervised learning technique which is extensively applied in the training of multi-layer feed-forward neural networks. Many modifications have been proposed to improve the performance of BP, and BP with Magnified Gradient Function (MGFPROP) is one of the fast learning algorithms which improve both the convergence rate and the global convergence capability of BP [19]. MGFPROP outperforms many benchmarking fast learning algorithms in different adaptive problems [19]. However, the performance of MGFPROP is limited due to the error overshooting problem. This paper presents a new approach called BP with Two-Phase Magnified Gradient Function (2P-MGFPROP) to overcome the error overshooting problem and hence speed up the convergence rate of MGFPROP. 2P-MGFPROP is modified from MGFPROP. It divides the learning process into two phases and adjusts the parameter setting of MGFPROP based on the nature of the phase of the learning process. Through simulation results in two different adaptive problems, 2P-MGFPROP outperforms MGFPROP with optimal parameter setting in terms of the convergence rate, and the improvement can be up to 50%.
ISBN: 978-1-4244-1820-6
978-1-4244-1821-3 (E-ISBN)
DOI: 10.1109/IJCNN.2008.4633873
Appears in Collections:Conference Paper

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Jul 10, 2018

Page view(s)

Last Week
Last month
Citations as of Jul 16, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.