A polynomial time algorithm for the construction and training of a class of multilayer perceptrons

Asim Roy; Lark Sang Kim; Somnath Mukhopadhyay

doi:10.1016/S0893-6080(05)80057-7

A polynomial time algorithm for the construction and training of a class of multilayer perceptrons

Asim Roy, Lark Sang Kim, Somnath Mukhopadhyay

Business, W. P. Carey School of (WPC)

Research output: Contribution to journal › Article › peer-review

68 Scopus citations

Abstract

This paper presents a polynomial time algorithm for the construction and training of a class of multilayer perceptrons for classification. It uses linear programming models to incrementally generate the hidden layer in a restricted higher-order perceptron. Polynomial time complexity of the method is proven. Computational results are provided for several well-known applications in the areas of speech recognition, medical diagnosis, and target detection. In all cases, very small nets were created that had error rates similar to those reported so far.

Original language	English (US)
Pages (from-to)	535-545
Number of pages	11
Journal	Neural Networks
Volume	6
Issue number	4
DOIs	https://doi.org/10.1016/S0893-6080(05)80057-7
State	Published - 1993

Keywords

Classification algorithm
Clustering
Linear programming
Multilayer perceptrons
Net design
Polynomial time algorithm
Supervised learning

ASJC Scopus subject areas

Cognitive Neuroscience
Artificial Intelligence

Access to Document

10.1016/S0893-6080(05)80057-7

Cite this

@article{6abd1e22ee574fea89af9086f083fcd5,

title = "A polynomial time algorithm for the construction and training of a class of multilayer perceptrons",

abstract = "This paper presents a polynomial time algorithm for the construction and training of a class of multilayer perceptrons for classification. It uses linear programming models to incrementally generate the hidden layer in a restricted higher-order perceptron. Polynomial time complexity of the method is proven. Computational results are provided for several well-known applications in the areas of speech recognition, medical diagnosis, and target detection. In all cases, very small nets were created that had error rates similar to those reported so far.",

keywords = "Classification algorithm, Clustering, Linear programming, Multilayer perceptrons, Net design, Polynomial time algorithm, Supervised learning",

author = "Asim Roy and Kim, {Lark Sang} and Somnath Mukhopadhyay",

note = "Funding Information: Acknowledgement: This research was supported, in part, by the National Science Foundation grant IRI-9113370.",

year = "1993",

doi = "10.1016/S0893-6080(05)80057-7",

language = "English (US)",

volume = "6",

pages = "535--545",

journal = "Neural Networks",

issn = "0893-6080",

publisher = "Elsevier Limited",

number = "4",

}

TY - JOUR

T1 - A polynomial time algorithm for the construction and training of a class of multilayer perceptrons

AU - Roy, Asim

AU - Kim, Lark Sang

AU - Mukhopadhyay, Somnath

N1 - Funding Information: Acknowledgement: This research was supported, in part, by the National Science Foundation grant IRI-9113370.

PY - 1993

Y1 - 1993

N2 - This paper presents a polynomial time algorithm for the construction and training of a class of multilayer perceptrons for classification. It uses linear programming models to incrementally generate the hidden layer in a restricted higher-order perceptron. Polynomial time complexity of the method is proven. Computational results are provided for several well-known applications in the areas of speech recognition, medical diagnosis, and target detection. In all cases, very small nets were created that had error rates similar to those reported so far.

AB - This paper presents a polynomial time algorithm for the construction and training of a class of multilayer perceptrons for classification. It uses linear programming models to incrementally generate the hidden layer in a restricted higher-order perceptron. Polynomial time complexity of the method is proven. Computational results are provided for several well-known applications in the areas of speech recognition, medical diagnosis, and target detection. In all cases, very small nets were created that had error rates similar to those reported so far.

KW - Classification algorithm

KW - Clustering

KW - Linear programming

KW - Multilayer perceptrons

KW - Net design

KW - Polynomial time algorithm

KW - Supervised learning

UR - http://www.scopus.com/inward/record.url?scp=0027259956&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027259956&partnerID=8YFLogxK

U2 - 10.1016/S0893-6080(05)80057-7

DO - 10.1016/S0893-6080(05)80057-7

M3 - Article

AN - SCOPUS:0027259956

SN - 0893-6080

VL - 6

SP - 535

EP - 545

JO - Neural Networks

JF - Neural Networks

IS - 4

ER -

A polynomial time algorithm for the construction and training of a class of multilayer perceptrons

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this