Please use this identifier to cite or link to this item: https://doi.org/10.1109/TNN.2006.880582
Title: Estimating the number of hidden neurons in a feedforward network using the singular value decomposition
Authors: Teoh, E.J.
Tan, K.C. 
Xiang, C. 
Issue Date: Nov-2006
Source: Teoh, E.J., Tan, K.C., Xiang, C. (2006-11). Estimating the number of hidden neurons in a feedforward network using the singular value decomposition. IEEE Transactions on Neural Networks 17 (6) : 1623-1629. ScholarBank@NUS Repository. https://doi.org/10.1109/TNN.2006.880582
Abstract: In this letter, we attempt to quantify the significance of increasing the number of neurons in the hidden layer of a feedforward neural network architecture using the singular value decomposition (SVD). Through this, we extend some well-known properties of the SVD in evaluating the generalizability of single hidden layer feedforward networks (SLFNs) with respect to the number of hidden layer neurons. The generalization capability of the SLFN is measured by the degree of linear independency of the patterns in hidden layer space, which can be indirectly quantified from the singular values obtained from the SVD, in a postlearning step. A pruning/growing technique based on these singular values is then used to estimate the necessary number of neurons in the hidden layer. More importantly, we describe in detail properties of the SVD in determining the structure of a neural network particularly with respect to the robustness of the selected model. © 2006 IEEE.
Source Title: IEEE Transactions on Neural Networks
URI: http://scholarbank.nus.edu.sg/handle/10635/50917
ISSN: 10459227
DOI: 10.1109/TNN.2006.880582
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

70
checked on Dec 7, 2017

WEB OF SCIENCETM
Citations

53
checked on Nov 29, 2017

Page view(s)

39
checked on Dec 11, 2017

Google ScholarTM

Check

Altmetric


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