Superior training of artificial neural networks using weight-space partitioning

H. V. Gupta; Kuo Lin Hsu; S. Sorooshian

doi:10.1109/ICNN.1997.614192

Superior training of artificial neural networks using weight-space partitioning

H. V. Gupta, Kuo Lin Hsu, S. Sorooshian

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

17 Scopus citations

Abstract

Linear least squares simplex (LLSSIM) is a new algorithm for batch training of three-layer feedforward artificial neural networks (ANN), based on a partitioning of the weight space. The input-hidden weights are trained using a «multi-start downhill simplex» global search algorithm, and the hidden-output weights are estimated using «conditional linear least squares». Monte-Carlo testing shows that LLSSIM provides globally superior weight estimates with significantly fewer function evaluations than the conventional backpropagation, adaptive backpropagation, and conjugate gradient strategies.

Original language	English (US)
Title of host publication	1997 IEEE International Conference on Neural Networks, ICNN 1997
Pages	1919-1923
Number of pages	5
DOIs	https://doi.org/10.1109/ICNN.1997.614192
State	Published - 1997
Event	1997 IEEE International Conference on Neural Networks, ICNN 1997 - Houston, TX, United States Duration: Jun 9 1997 → Jun 12 1997

Publication series

Name	IEEE International Conference on Neural Networks - Conference Proceedings
Volume	3
ISSN (Print)	1098-7576

Conference

Conference	1997 IEEE International Conference on Neural Networks, ICNN 1997
Country/Territory	United States
City	Houston, TX
Period	6/9/97 → 6/12/97

ASJC Scopus subject areas

Software

Access to Document

10.1109/ICNN.1997.614192

Cite this

Superior training of artificial neural networks using weight-space partitioning. / Gupta, H. V.; Hsu, Kuo Lin; Sorooshian, S.
1997 IEEE International Conference on Neural Networks, ICNN 1997. 1997. p. 1919-1923 614192 (IEEE International Conference on Neural Networks - Conference Proceedings; Vol. 3).

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

Gupta, HV, Hsu, KL & Sorooshian, S 1997, Superior training of artificial neural networks using weight-space partitioning. in 1997 IEEE International Conference on Neural Networks, ICNN 1997., 614192, IEEE International Conference on Neural Networks - Conference Proceedings, vol. 3, pp. 1919-1923, 1997 IEEE International Conference on Neural Networks, ICNN 1997, Houston, TX, United States, 6/9/97. https://doi.org/10.1109/ICNN.1997.614192

@inproceedings{ee4b4693b285438fba8157a86ae9794d,

title = "Superior training of artificial neural networks using weight-space partitioning",

abstract = "Linear least squares simplex (LLSSIM) is a new algorithm for batch training of three-layer feedforward artificial neural networks (ANN), based on a partitioning of the weight space. The input-hidden weights are trained using a «multi-start downhill simplex» global search algorithm, and the hidden-output weights are estimated using «conditional linear least squares». Monte-Carlo testing shows that LLSSIM provides globally superior weight estimates with significantly fewer function evaluations than the conventional backpropagation, adaptive backpropagation, and conjugate gradient strategies.",

author = "Gupta, {H. V.} and Hsu, {Kuo Lin} and S. Sorooshian",

year = "1997",

doi = "10.1109/ICNN.1997.614192",

language = "English (US)",

isbn = "0780341228",

series = "IEEE International Conference on Neural Networks - Conference Proceedings",

pages = "1919--1923",

booktitle = "1997 IEEE International Conference on Neural Networks, ICNN 1997",

note = "1997 IEEE International Conference on Neural Networks, ICNN 1997 ; Conference date: 09-06-1997 Through 12-06-1997",

}

TY - GEN

T1 - Superior training of artificial neural networks using weight-space partitioning

AU - Gupta, H. V.

AU - Hsu, Kuo Lin

AU - Sorooshian, S.

PY - 1997

Y1 - 1997

N2 - Linear least squares simplex (LLSSIM) is a new algorithm for batch training of three-layer feedforward artificial neural networks (ANN), based on a partitioning of the weight space. The input-hidden weights are trained using a «multi-start downhill simplex» global search algorithm, and the hidden-output weights are estimated using «conditional linear least squares». Monte-Carlo testing shows that LLSSIM provides globally superior weight estimates with significantly fewer function evaluations than the conventional backpropagation, adaptive backpropagation, and conjugate gradient strategies.

AB - Linear least squares simplex (LLSSIM) is a new algorithm for batch training of three-layer feedforward artificial neural networks (ANN), based on a partitioning of the weight space. The input-hidden weights are trained using a «multi-start downhill simplex» global search algorithm, and the hidden-output weights are estimated using «conditional linear least squares». Monte-Carlo testing shows that LLSSIM provides globally superior weight estimates with significantly fewer function evaluations than the conventional backpropagation, adaptive backpropagation, and conjugate gradient strategies.

UR - http://www.scopus.com/inward/record.url?scp=0030682699&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030682699&partnerID=8YFLogxK

U2 - 10.1109/ICNN.1997.614192

DO - 10.1109/ICNN.1997.614192

M3 - Conference contribution

AN - SCOPUS:0030682699

SN - 0780341228

SN - 9780780341227

T3 - IEEE International Conference on Neural Networks - Conference Proceedings

SP - 1919

EP - 1923

BT - 1997 IEEE International Conference on Neural Networks, ICNN 1997

T2 - 1997 IEEE International Conference on Neural Networks, ICNN 1997

Y2 - 9 June 1997 through 12 June 1997

ER -

Superior training of artificial neural networks using weight-space partitioning

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this