A stochastic learning algorithm for generalization problems

C. V. Ramamoorthy; Shashi Shekhar

A stochastic learning algorithm for generalization problems

Computer Science and Engineering

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

Abstract

A discussion is presented of the requirements of learning for generalization, which is NP-complete and cannot be addressed by traditional methods based on gradient descent. The authors present a stochastic learning algorithm based on simulated annealing in weight space and discuss stopping criteria for the algorithm, to avoid overfitting of learning examples.

Original language	English (US)
Title of host publication	TENCON '89
Subtitle of host publication	Fourth IEEE Region 10 International Conference
Publisher	Publ by IEEE
Pages	136-141
Number of pages	6
State	Published - Dec 1 1989
Event	4th IEEE Region 10th International Conference - TENCON '89 - Bombay, India Duration: Nov 22 1989 → Nov 24 1989

Other

Other	4th IEEE Region 10th International Conference - TENCON '89
City	Bombay, India
Period	11/22/89 → 11/24/89

Find It

Find It at U of M Libraries

Cite this

@inproceedings{d621de9285054359ae4e03e8f43308a3,

title = "A stochastic learning algorithm for generalization problems",

abstract = "A discussion is presented of the requirements of learning for generalization, which is NP-complete and cannot be addressed by traditional methods based on gradient descent. The authors present a stochastic learning algorithm based on simulated annealing in weight space and discuss stopping criteria for the algorithm, to avoid overfitting of learning examples.",

author = "Ramamoorthy, {C. V.} and Shashi Shekhar",

year = "1989",

month = dec,

day = "1",

language = "English (US)",

pages = "136--141",

booktitle = "TENCON '89",

publisher = "Publ by IEEE",

note = "4th IEEE Region 10th International Conference - TENCON '89 ; Conference date: 22-11-1989 Through 24-11-1989",

}

TY - GEN

T1 - A stochastic learning algorithm for generalization problems

AU - Ramamoorthy, C. V.

AU - Shekhar, Shashi

PY - 1989/12/1

Y1 - 1989/12/1

N2 - A discussion is presented of the requirements of learning for generalization, which is NP-complete and cannot be addressed by traditional methods based on gradient descent. The authors present a stochastic learning algorithm based on simulated annealing in weight space and discuss stopping criteria for the algorithm, to avoid overfitting of learning examples.

AB - A discussion is presented of the requirements of learning for generalization, which is NP-complete and cannot be addressed by traditional methods based on gradient descent. The authors present a stochastic learning algorithm based on simulated annealing in weight space and discuss stopping criteria for the algorithm, to avoid overfitting of learning examples.

UR - http://www.scopus.com/inward/record.url?scp=0024774428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024774428&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0024774428

SP - 136

EP - 141

BT - TENCON '89

PB - Publ by IEEE

T2 - 4th IEEE Region 10th International Conference - TENCON '89

Y2 - 22 November 1989 through 24 November 1989

ER -

A stochastic learning algorithm for generalization problems

Abstract

Other

Find It

Other files and links

Fingerprint

Cite this