Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/37748
Title: Solving the local minimum and flat-spot problem by modifying wrong outputs for feed-forward neural networks
Authors: Cheung, CC
Ng, SC
Lui, AK
Xu, SS
Keywords: Backpropagation
Convergence
Feedforward neural nets
Statistical analysis
Issue Date: 2013
Source: Proceedings of the International Joint Conference on Neural Networks (IJCNN’2013), Dallas, TX, 4-9 Aug. 2013, p. 1-7 How to cite?
Abstract: Backpropagation (BP) algorithm, which is very popular in supervised learning, is extensively applied in training feed-forward neural networks. Many modifications have been proposed to speed up the convergence process of the standard BP algorithm. However, they seldom focus on improving the global convergence capability. This paper proposes a new algorithm called Wrong Output Modification (WOM) to improve the global convergence capability of a fast learning algorithm. When a learning process is trapped by a local minimum or a flat-spot area, this algorithm looks for some outputs that go to other extremes when compared with their target outputs, and then it modifies such outputs systemically so that they can get close to their target outputs and hence some weights of neurons are changed accordingly. It is hoped that these changes make the learning process escape from such local minima or flat-spot areas and then converge. The performance investigation shows that the proposed algorithm can be applied into different fast learning algorithms, and their global convergence capabilities are improved significantly compared with their original algorithms. Moreover, some statistical data obtained from this algorithm can be used to identify the difficulty of a learning problem.
URI: http://hdl.handle.net/10397/37748
ISBN: 978-1-4673-6128-6
DOI: 10.1109/IJCNN.2013.6706913
Appears in Collections:Conference Paper

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

SCOPUSTM   
Citations

3
Citations as of Sep 18, 2017

Page view(s)

34
Last Week
5
Last month
Checked on Sep 18, 2017

Google ScholarTM

Check

Altmetric



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