Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/37746
Title: A fast learning algorithm with promising convergence capability
Authors: Cheung, CC
Ng, SC
Lui, AK
Xu, SS
Keywords: Backpropagation
Feedforward neural nets
Issue Date: 2011
Source: Proceedings of the International Joint Conference on Neural Networks (IJCNN'2011), San Jose, CA, July 31 2011-Aug. 5 2011, p. 937-942 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 of BP have been proposed to speed up the learning of the original BP. However, these modifications sometimes cannot converge properly due to the local minimum problem. This paper proposes a new algorithm, which provides a systematic approach to make use of the characteristics of different fast learning algorithms so that the convergence of a learning process is promising with a fast learning rate. Our performance investigation shows that the proposed algorithm always converges with a fast learning rate in two popular complicated applications whereas other popular fast learning algorithms give very poor global convergence capabilities in these two applications.
URI: http://hdl.handle.net/10397/37746
ISBN: 978-1-4244-9635-8
ISSN: 2161-4393
DOI: 10.1109/IJCNN.2011.6033323
Appears in Collections:Conference Paper

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

Page view(s)

31
Last Week
5
Last month
Checked on Aug 14, 2017

Google ScholarTM

Check

Altmetric



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