Iterative generation of higher-order nets in polynomial time using linear programming

Asim Roy; Somnath Mukhopadhyay

doi:10.1109/72.557694

Iterative generation of higher-order nets in polynomial time using linear programming

Asim Roy, Somnath Mukhopadhyay

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

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

12 Scopus citations

Abstract

This paper presents an algorithm for constructing and training a class of higher-order perceptrons for classification problems. The method uses linear programming models to construct and train the net. Its polynomial time complexity is proven and computational results are provided for several well-known problems. In all cases, very small nets were created compared to those reported in other computational studies.

Original language	English (US)
Pages (from-to)	402-412
Number of pages	11
Journal	IEEE Transactions on Neural Networks
Volume	8
Issue number	2
DOIs	https://doi.org/10.1109/72.557694
State	Published - 1997

Keywords

Designing neural networks
Feedforward nets
Higher-order networks
Learning complexity
Linear programming
Multilayer perceptrons
Polynomial time complexity

ASJC Scopus subject areas

Software
Computer Science Applications
Computer Networks and Communications
Artificial Intelligence

Access to Document

10.1109/72.557694

Cite this

@article{ef4353b79c96487fb39b03a7af3a96b6,

title = "Iterative generation of higher-order nets in polynomial time using linear programming",

abstract = "This paper presents an algorithm for constructing and training a class of higher-order perceptrons for classification problems. The method uses linear programming models to construct and train the net. Its polynomial time complexity is proven and computational results are provided for several well-known problems. In all cases, very small nets were created compared to those reported in other computational studies.",

keywords = "Designing neural networks, Feedforward nets, Higher-order networks, Learning complexity, Linear programming, Multilayer perceptrons, Polynomial time complexity",

author = "Asim Roy and Somnath Mukhopadhyay",

note = "Funding Information: Manuscript received June 25, 1995; revised June 12, 1996 and October 21, 1996. This work was supported in part by the National Science Foundation Grant IRI-9113370 and by the College of Business Summer Research Grants. The authors are with the Department of Decision and Information Systems, Arizona State University, Tempe, AZ 85287–4206 USA. Publisher Item Identifier S 1045-9227(97)01757-8.",

year = "1997",

doi = "10.1109/72.557694",

language = "English (US)",

volume = "8",

pages = "402--412",

journal = "IEEE Transactions on Neural Networks",

issn = "1045-9227",

publisher = "IEEE Computational Intelligence Society",

number = "2",

}

TY - JOUR

T1 - Iterative generation of higher-order nets in polynomial time using linear programming

AU - Roy, Asim

AU - Mukhopadhyay, Somnath

N1 - Funding Information: Manuscript received June 25, 1995; revised June 12, 1996 and October 21, 1996. This work was supported in part by the National Science Foundation Grant IRI-9113370 and by the College of Business Summer Research Grants. The authors are with the Department of Decision and Information Systems, Arizona State University, Tempe, AZ 85287–4206 USA. Publisher Item Identifier S 1045-9227(97)01757-8.

PY - 1997

Y1 - 1997

N2 - This paper presents an algorithm for constructing and training a class of higher-order perceptrons for classification problems. The method uses linear programming models to construct and train the net. Its polynomial time complexity is proven and computational results are provided for several well-known problems. In all cases, very small nets were created compared to those reported in other computational studies.

AB - This paper presents an algorithm for constructing and training a class of higher-order perceptrons for classification problems. The method uses linear programming models to construct and train the net. Its polynomial time complexity is proven and computational results are provided for several well-known problems. In all cases, very small nets were created compared to those reported in other computational studies.

KW - Designing neural networks

KW - Feedforward nets

KW - Higher-order networks

KW - Learning complexity

KW - Linear programming

KW - Multilayer perceptrons

KW - Polynomial time complexity

UR - http://www.scopus.com/inward/record.url?scp=0031097230&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031097230&partnerID=8YFLogxK

U2 - 10.1109/72.557694

DO - 10.1109/72.557694

M3 - Article

C2 - 18255642

SN - 1045-9227

VL - 8

SP - 402

EP - 412

JO - IEEE Transactions on Neural Networks

JF - IEEE Transactions on Neural Networks

IS - 2

ER -

Iterative generation of higher-order nets in polynomial time using linear programming

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this