Enhancing the Generalization Ability of Neural Networks by Using Gram-Schmidt Orthogonalization Algorithm

Weishui WAN; Kotaro HIRASAWA; Jinglu HU

doi:10.9746/sicetr1965.39.697

Transactions of the Society of Instrument and Control Engineers

Online ISSN : 1883-8189
Print ISSN : 0453-4654
ISSN-L : 0453-4654

Enhancing the Generalization Ability of Neural Networks by Using Gram-Schmidt Orthogonalization Algorithm

Weishui WAN, Kotaro HIRASAWA, Jinglu HU

Author information

Keywords: generalization, gram-schmidt orthogonalization algorithm, regularizer, optimal brain damage

JOURNAL FREE ACCESS

2003 Volume 39 Issue 7 Pages 697-698

DOI https://doi.org/10.9746/sicetr1965.39.697

Details

Abstract

In this paper a new algorithm applying Gram-Schmidt orthogonalization algorithm to the outputs of nodes in the hidden layers is proposed with the aim to reduce the interference among the nodes in the hidden layers, therefore to enhance the generalization ability of neural networks, which is much more efficient than other regularizers methods. Simulation results confirm the above assertion.

Content from these authors

Favorites & Alerts

Corresponding author

Register with J-STAGE for free!