Constructive neural network learning algorithms

Rajesh Parekh, Jihoon Yang, Vasant Honavar

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

Abstract

Constructive algorithms can increase the construction of potentially minimal neural network architectures for pattern classification tasks. These algorithms have a set of inductive and representational biases implicit in the design choices that determine where to add neurons and how to train and prune them. The biases that best suit the needs of each individual classification tasks are then systematically characterized.

Original languageEnglish (US)
Title of host publicationProceedings of the National Conference on Artificial Intelligence
Editors Anon
PublisherAAAI
Pages1398
Number of pages1
Volume2
StatePublished - 1996
EventProceedings of the 1996 13th National Conference on Artificial Intelligence. Part 2 (of 2) - Portland, OR, USA
Duration: Aug 4 1996Aug 8 1996

Other

OtherProceedings of the 1996 13th National Conference on Artificial Intelligence. Part 2 (of 2)
CityPortland, OR, USA
Period8/4/968/8/96

Fingerprint

Learning algorithms
Neural networks
Network architecture
Neurons
Pattern recognition

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Parekh, R., Yang, J., & Honavar, V. (1996). Constructive neural network learning algorithms. In Anon (Ed.), Proceedings of the National Conference on Artificial Intelligence (Vol. 2, pp. 1398). AAAI.
Parekh, Rajesh ; Yang, Jihoon ; Honavar, Vasant. / Constructive neural network learning algorithms. Proceedings of the National Conference on Artificial Intelligence. editor / Anon. Vol. 2 AAAI, 1996. pp. 1398
@inproceedings{9b4c6372119b49df9c9d00754720f814,
title = "Constructive neural network learning algorithms",
abstract = "Constructive algorithms can increase the construction of potentially minimal neural network architectures for pattern classification tasks. These algorithms have a set of inductive and representational biases implicit in the design choices that determine where to add neurons and how to train and prune them. The biases that best suit the needs of each individual classification tasks are then systematically characterized.",
author = "Rajesh Parekh and Jihoon Yang and Vasant Honavar",
year = "1996",
language = "English (US)",
volume = "2",
pages = "1398",
editor = "Anon",
booktitle = "Proceedings of the National Conference on Artificial Intelligence",
publisher = "AAAI",

}

Parekh, R, Yang, J & Honavar, V 1996, Constructive neural network learning algorithms. in Anon (ed.), Proceedings of the National Conference on Artificial Intelligence. vol. 2, AAAI, pp. 1398, Proceedings of the 1996 13th National Conference on Artificial Intelligence. Part 2 (of 2), Portland, OR, USA, 8/4/96.

Constructive neural network learning algorithms. / Parekh, Rajesh; Yang, Jihoon; Honavar, Vasant.

Proceedings of the National Conference on Artificial Intelligence. ed. / Anon. Vol. 2 AAAI, 1996. p. 1398.

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

TY - GEN

T1 - Constructive neural network learning algorithms

AU - Parekh, Rajesh

AU - Yang, Jihoon

AU - Honavar, Vasant

PY - 1996

Y1 - 1996

N2 - Constructive algorithms can increase the construction of potentially minimal neural network architectures for pattern classification tasks. These algorithms have a set of inductive and representational biases implicit in the design choices that determine where to add neurons and how to train and prune them. The biases that best suit the needs of each individual classification tasks are then systematically characterized.

AB - Constructive algorithms can increase the construction of potentially minimal neural network architectures for pattern classification tasks. These algorithms have a set of inductive and representational biases implicit in the design choices that determine where to add neurons and how to train and prune them. The biases that best suit the needs of each individual classification tasks are then systematically characterized.

UR - http://www.scopus.com/inward/record.url?scp=0030349502&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030349502&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030349502

VL - 2

SP - 1398

BT - Proceedings of the National Conference on Artificial Intelligence

A2 - Anon, null

PB - AAAI

ER -

Parekh R, Yang J, Honavar V. Constructive neural network learning algorithms. In Anon, editor, Proceedings of the National Conference on Artificial Intelligence. Vol. 2. AAAI. 1996. p. 1398