Back to Search Start Over

Orthogonal Least Squares Algorithm for Training Cascade Neural Networks.

Authors :
Gao Huang
Shiji Song
Cheng Wu
Source :
IEEE Transactions on Circuits & Systems. Part I: Regular Papers; Nov2012, Vol. 59 Issue 11, p2629-2637, 9p
Publication Year :
2012

Abstract

This paper proposes a novel constructive training algorithm for cascade neural networks. By reformulating the cascade neural network as a linear-in-the-parameters model, we use the orthogonal least squares (OLS) method to derive a novel objective function for training new hidden units. With this objective function, the sum of squared errors (SSE) of the network can be maximally reduced after each new hidden unit is added, thus leading to a network with less hidden units and better generalization performance. Furthermore, the proposed algorithm considers both the input weights training and output weights training in an integrated framework, which greatly simplifies the training of output weights. The effectiveness of the proposed algorithm is demonstrated by simulation results. [ABSTRACT FROM PUBLISHER]

Details

Language :
English
ISSN :
15498328
Volume :
59
Issue :
11
Database :
Complementary Index
Journal :
IEEE Transactions on Circuits & Systems. Part I: Regular Papers
Publication Type :
Periodical
Accession number :
101316797
Full Text :
https://doi.org/10.1109/TCSI.2012.2189060