Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/13489
Title: Feedforward networks training speed enhancement by optimal initialization of the synaptic coefficients
Authors: Yam, JYF
Chow, TWS
Issue Date: 2001
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on neural networks, 2001, v. 12, no. 2, p. 430-434 How to cite?
Journal: IEEE transactions on neural networks 
Abstract: This letter aims at determining the optimal bias and magnitude of initial weight vectors based on multidimensional geometry. This method ensures the outputs of neurons are in the active region and the range of the activation function is fully utilized. In this letter, very thorough simulations and comparative study were performed to validate the performance of the proposed method. The obtained results on five well-known benchmark problems demonstrate that the proposed method deliver consistent good results compared with other weight initialization methods
URI: http://hdl.handle.net/10397/13489
ISSN: 1045-9227
DOI: 10.1109/72.914538
Appears in Collections:Journal/Magazine Article

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

SCOPUSTM   
Citations

68
Last Week
1
Last month
Citations as of Apr 16, 2018

WEB OF SCIENCETM
Citations

49
Last Week
0
Last month
0
Citations as of Apr 23, 2018

Page view(s)

49
Last Week
4
Last month
Citations as of Apr 23, 2018

Google ScholarTM

Check

Altmetric


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