MUpstart - a constructive neural network learning algorithm for multi-category pattern classification

Rajesh Parekh, Jihoon Yang, Vasant Honavar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Constructive learning algorithms offer an approach for dynamically constructing near-minimal neural network architectures for pattern classification tasks. Several such algorithms proposed in the literature are shown to converge to zero classification errors on finite non-contradictory datasets. However, these algorithms are restricted to two-category pattern classification and (in most cases) they require the input patterns to have binary (or bipolar) valued attributes only. We present a probably correct extension of the Upstart algorithm to handle multiple output classes and real-valued pattern attributes. Results of experiments with several artificial and real-world datasets demonstrate the feasibility of this approach in practical pattern classification tasks and also suggest several interesting directions for future research.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
PublisherIEEE
Pages1924-1929
Number of pages6
Volume3
StatePublished - 1997
EventProceedings of the 1997 IEEE International Conference on Neural Networks. Part 4 (of 4) - Houston, TX, USA
Duration: Jun 9 1997Jun 12 1997

Other

OtherProceedings of the 1997 IEEE International Conference on Neural Networks. Part 4 (of 4)
CityHouston, TX, USA
Period6/9/976/12/97

Fingerprint

Learning algorithms
Pattern recognition
Neural networks
Network architecture
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence

Cite this

Parekh, R., Yang, J., & Honavar, V. (1997). MUpstart - a constructive neural network learning algorithm for multi-category pattern classification. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 3, pp. 1924-1929). IEEE.
Parekh, Rajesh ; Yang, Jihoon ; Honavar, Vasant. / MUpstart - a constructive neural network learning algorithm for multi-category pattern classification. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 3 IEEE, 1997. pp. 1924-1929
@inproceedings{85ba07ded207491aa44f029b5e349882,
title = "MUpstart - a constructive neural network learning algorithm for multi-category pattern classification",
abstract = "Constructive learning algorithms offer an approach for dynamically constructing near-minimal neural network architectures for pattern classification tasks. Several such algorithms proposed in the literature are shown to converge to zero classification errors on finite non-contradictory datasets. However, these algorithms are restricted to two-category pattern classification and (in most cases) they require the input patterns to have binary (or bipolar) valued attributes only. We present a probably correct extension of the Upstart algorithm to handle multiple output classes and real-valued pattern attributes. Results of experiments with several artificial and real-world datasets demonstrate the feasibility of this approach in practical pattern classification tasks and also suggest several interesting directions for future research.",
author = "Rajesh Parekh and Jihoon Yang and Vasant Honavar",
year = "1997",
language = "English (US)",
volume = "3",
pages = "1924--1929",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

Parekh, R, Yang, J & Honavar, V 1997, MUpstart - a constructive neural network learning algorithm for multi-category pattern classification. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 3, IEEE, pp. 1924-1929, Proceedings of the 1997 IEEE International Conference on Neural Networks. Part 4 (of 4), Houston, TX, USA, 6/9/97.

MUpstart - a constructive neural network learning algorithm for multi-category pattern classification. / Parekh, Rajesh; Yang, Jihoon; Honavar, Vasant.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 3 IEEE, 1997. p. 1924-1929.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - MUpstart - a constructive neural network learning algorithm for multi-category pattern classification

AU - Parekh, Rajesh

AU - Yang, Jihoon

AU - Honavar, Vasant

PY - 1997

Y1 - 1997

N2 - Constructive learning algorithms offer an approach for dynamically constructing near-minimal neural network architectures for pattern classification tasks. Several such algorithms proposed in the literature are shown to converge to zero classification errors on finite non-contradictory datasets. However, these algorithms are restricted to two-category pattern classification and (in most cases) they require the input patterns to have binary (or bipolar) valued attributes only. We present a probably correct extension of the Upstart algorithm to handle multiple output classes and real-valued pattern attributes. Results of experiments with several artificial and real-world datasets demonstrate the feasibility of this approach in practical pattern classification tasks and also suggest several interesting directions for future research.

AB - Constructive learning algorithms offer an approach for dynamically constructing near-minimal neural network architectures for pattern classification tasks. Several such algorithms proposed in the literature are shown to converge to zero classification errors on finite non-contradictory datasets. However, these algorithms are restricted to two-category pattern classification and (in most cases) they require the input patterns to have binary (or bipolar) valued attributes only. We present a probably correct extension of the Upstart algorithm to handle multiple output classes and real-valued pattern attributes. Results of experiments with several artificial and real-world datasets demonstrate the feasibility of this approach in practical pattern classification tasks and also suggest several interesting directions for future research.

UR - http://www.scopus.com/inward/record.url?scp=0030688750&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030688750&partnerID=8YFLogxK

M3 - Conference contribution

VL - 3

SP - 1924

EP - 1929

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

ER -

Parekh R, Yang J, Honavar V. MUpstart - a constructive neural network learning algorithm for multi-category pattern classification. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 3. IEEE. 1997. p. 1924-1929