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

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

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

W. Wan, K. Hirasawa^*, J. Hu, J. Murata

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

2 Citations (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
Pages	1721-1726
Number of pages	6
Publication status	Published - 2001 Jan 1
Externally published	Yes
Event	International Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, United States Duration: 2001 Jul 15 → 2001 Jul 19

Conference

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

ASJC Scopus subject areas

Software
Artificial Intelligence

Cite this

@conference{b2b44eaa4a3347e3920cb95e817624b3,

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 J. Murata",

year = "2001",

month = jan,

day = "1",

language = "English",

pages = "1721--1726",

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

}

TY - CONF

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, J.

PY - 2001/1/1

Y1 - 2001/1/1

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 - Paper

AN - SCOPUS:0034877843

SP - 1721

EP - 1726

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

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this