Enhancing the generalization ability of neural networks by using gram-schmidt orthogonalization algorithm

W. Wan; K. Hirasawa; J. Hu; Junichi Murata

Enhancing the generalization ability of neural networks by using gram-schmidt orthogonalization algorithm

W. Wan, K. Hirasawa, J. Hu, Junichi Murata

Section of Measurement and Control Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

Generalization ability of neural networks is the most important criterion to determine whether one algorithm is powerful or not. Many new algorithms have been devised to enhance the generalization ability of neural networks[1][2]. In this paper a new algorithm using the Gram-Schmidt orthogonalization algorithm [3] 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, which is much more efficient than the regularizers methods. Simulation results confirm the above assertion.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks
Pages	1721-1726
Number of pages	6
Volume	3
Publication status	Published - 2001
Event	International Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, United States Duration: Jul 15 2001 → Jul 19 2001

Other

Other	International Joint Conference on Neural Networks (IJCNN'01)
Country	United States
City	Washington, DC
Period	7/15/01 → 7/19/01

All Science Journal Classification (ASJC) codes

Software

Fingerprint Dive into the research topics of 'Enhancing the generalization ability of neural networks by using gram-schmidt orthogonalization algorithm'. Together they form a unique fingerprint.

Cite this

@inproceedings{0bb1c3785e674ba0a15d5cef322031f0,

title = "Enhancing the generalization ability of neural networks by using gram-schmidt orthogonalization algorithm",

abstract = "Generalization ability of neural networks is the most important criterion to determine whether one algorithm is powerful or not. Many new algorithms have been devised to enhance the generalization ability of neural networks[1][2]. In this paper a new algorithm using the Gram-Schmidt orthogonalization algorithm [3] 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, which is much more efficient than the regularizers methods. Simulation results confirm the above assertion.",

author = "W. Wan and K. Hirasawa and J. Hu and Junichi Murata",

year = "2001",

language = "English",

volume = "3",

pages = "1721--1726",

booktitle = "Proceedings of the International Joint Conference on Neural Networks",

note = "International Joint Conference on Neural Networks (IJCNN'01) ; Conference date: 15-07-2001 Through 19-07-2001",

}

TY - GEN

T1 - Enhancing the generalization ability of neural networks by using gram-schmidt orthogonalization algorithm

AU - Wan, W.

AU - Hirasawa, K.

AU - Hu, J.

AU - Murata, Junichi

PY - 2001

Y1 - 2001

N2 - Generalization ability of neural networks is the most important criterion to determine whether one algorithm is powerful or not. Many new algorithms have been devised to enhance the generalization ability of neural networks[1][2]. In this paper a new algorithm using the Gram-Schmidt orthogonalization algorithm [3] 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, which is much more efficient than the regularizers methods. Simulation results confirm the above assertion.

AB - Generalization ability of neural networks is the most important criterion to determine whether one algorithm is powerful or not. Many new algorithms have been devised to enhance the generalization ability of neural networks[1][2]. In this paper a new algorithm using the Gram-Schmidt orthogonalization algorithm [3] 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, which is much more efficient than the regularizers methods. Simulation results confirm the above assertion.

UR - http://www.scopus.com/inward/record.url?scp=0034877843&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034877843&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0034877843

VL - 3

SP - 1721

EP - 1726

BT - Proceedings of the International Joint Conference on Neural Networks

T2 - International Joint Conference on Neural Networks (IJCNN'01)

Y2 - 15 July 2001 through 19 July 2001

ER -

Enhancing the generalization ability of neural networks by using gram-schmidt orthogonalization algorithm

Abstract

Other

All Science Journal Classification (ASJC) codes

Other files and links

Cite this