Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/55599
Title: A new terminating condition to identify the convergence of the learning process in multi-layer feed-forward neural networks
Authors: Xu, SS
Cheung, CC
Keywords: Breast
Cancer
Iris
Issue Date: 2015
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source: Proceedings of the International Joint Conference on Neural Networks, IJCNN 2015, 12-17 July 2015, 7280435 How to cite?
Abstract: Multi-layer feed-forward neural networks are commonly used in supervised learning, for which data training is required. One popular way to check whether the training is completed is to monitor the mean square error. It is expected that the learning is completed when the mean square error is less than or equal to an error threshold, which is usually a very small positive real number (e.g., 0.001). However, this terminating condition does not always work very effectively. This paper proposes a new terminating condition to identify the convergence of the learning process in multi-layer feed-forward neural networks. The new termination condition is called Threshold of Output Differences (TOD), which is the difference between an ouput value and its corresponding desired (target) output value to identify the convergence of the learning process. It proposes that the learning is completed when the difference for each output is less than a threshold. The performance investigation showed that the convergence rate of a learning algorithm with this new terminating condition is generally faster than the original one. Moreover, the classification rate (generalization) of a learning algorithm with TOD is usually better than the original one.
URI: http://hdl.handle.net/10397/55599
ISBN: 9781479919604
DOI: 10.1109/IJCNN.2015.7280435
Appears in Collections:Conference Paper

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

Page view(s)

37
Last Week
1
Last month
Checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric



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