Synchronous learning versus asynchronous learning in artificial neural networks

Jun Wang

doi:10.1109/icsyse.1991.161109

Synchronous learning versus asynchronous learning in artificial neural networks

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

Conditions of configuring feedforward neural networks without local minima are analyzed for both synchronous and asynchronous learning rules. Based on the analysis, a learning algorithm that integrates a synchronous-asynchronous learning rule with a dynamic configuration rule to train feedforward neural networks is presented. The theoretic analysis and numerical simulation reveal that the proposed learning algorithm substantially reduces the likelihood of local minimum solutions in supervised learning.

Original language	English
Title of host publication	Proceedings of the IEEE International Conference on Systems Engineering 1991
Publisher	IEEE
Pages	185-188
ISBN (Print)	780301730
DOIs	https://doi.org/10.1109/icsyse.1991.161109
Publication status	Published - Aug 1991
Externally published	Yes
Event	IEEE International Conference on Systems Engineering 1991 - Dayton, United States Duration: 1 Aug 1991 → 3 Aug 1991

Conference

Conference	IEEE International Conference on Systems Engineering 1991
Place	United States
City	Dayton
Period	1/08/91 → 3/08/91

Access Output

10.1109/icsyse.1991.161109

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{e23e4039439949a5a6e3c6af79eccc2c,

title = "Synchronous learning versus asynchronous learning in artificial neural networks",

abstract = "Conditions of configuring feedforward neural networks without local minima are analyzed for both synchronous and asynchronous learning rules. Based on the analysis, a learning algorithm that integrates a synchronous-asynchronous learning rule with a dynamic configuration rule to train feedforward neural networks is presented. The theoretic analysis and numerical simulation reveal that the proposed learning algorithm substantially reduces the likelihood of local minimum solutions in supervised learning.",

author = "Jun Wang",

year = "1991",

month = aug,

doi = "10.1109/icsyse.1991.161109",

language = "English",

isbn = "780301730",

pages = "185--188",

booktitle = "Proceedings of the IEEE International Conference on Systems Engineering 1991",

publisher = "IEEE",

address = "United States",

note = "IEEE International Conference on Systems Engineering 1991 ; Conference date: 01-08-1991 Through 03-08-1991",

}

TY - GEN

T1 - Synchronous learning versus asynchronous learning in artificial neural networks

AU - Wang, Jun

PY - 1991/8

Y1 - 1991/8

N2 - Conditions of configuring feedforward neural networks without local minima are analyzed for both synchronous and asynchronous learning rules. Based on the analysis, a learning algorithm that integrates a synchronous-asynchronous learning rule with a dynamic configuration rule to train feedforward neural networks is presented. The theoretic analysis and numerical simulation reveal that the proposed learning algorithm substantially reduces the likelihood of local minimum solutions in supervised learning.

AB - Conditions of configuring feedforward neural networks without local minima are analyzed for both synchronous and asynchronous learning rules. Based on the analysis, a learning algorithm that integrates a synchronous-asynchronous learning rule with a dynamic configuration rule to train feedforward neural networks is presented. The theoretic analysis and numerical simulation reveal that the proposed learning algorithm substantially reduces the likelihood of local minimum solutions in supervised learning.

UR - http://www.scopus.com/inward/record.url?scp=0026387442&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0026387442&origin=recordpage

U2 - 10.1109/icsyse.1991.161109

DO - 10.1109/icsyse.1991.161109

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 780301730

SP - 185

EP - 188

BT - Proceedings of the IEEE International Conference on Systems Engineering 1991

PB - IEEE

T2 - IEEE International Conference on Systems Engineering 1991

Y2 - 1 August 1991 through 3 August 1991

ER -

Synchronous learning versus asynchronous learning in artificial neural networks

Abstract

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this