Constructive theory refinement in knowledge based neural networks

Rajesh Parekh, Vasant Honavar

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

11 Citations (Scopus)

Abstract

Knowledge based artificial neural networks offer an approach for connectionist theory refinement. We present an algorithm for refining and extending the domain theory incorporated in a knowledge based neural network using constructive neural network learning algorithms. The initial domain theory comprising of propositional rules is translated into a knowledge based network of threshold logic units (threshold neuron). The domain theory is modified by dynamically adding neurons to the existing network. A constructive neural network learning algorithm is used to add and train these additional neurons using a sequence of labeled examples. We propose a novel hybrid constructive learning algorithm based on the Tiling and Pyramid constructive learning algorithms that allows knowledge based neural network to handle patterns with continuous valued attributes. Results of experiments on two non-trivial tasks (the ribosome binding site prediction and the financial advisor) show that our algorithm compares favorably with other algorithms for connectionist theory refinement both in terms of generalization accuracy and network size.

Original languageEnglish (US)
Title of host publicationIEEE World Congress on Computational Intelligence
Editors Anon
PublisherIEEE
Pages2318-2323
Number of pages6
Volume3
StatePublished - 1998
EventProceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3) - Anchorage, AK, USA
Duration: May 4 1998May 9 1998

Other

OtherProceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3)
CityAnchorage, AK, USA
Period5/4/985/9/98

Fingerprint

Learning algorithms
Neural networks
Neurons
Threshold logic
Binding sites
Refining
Experiments

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Parekh, R., & Honavar, V. (1998). Constructive theory refinement in knowledge based neural networks. In Anon (Ed.), IEEE World Congress on Computational Intelligence (Vol. 3, pp. 2318-2323). IEEE.
Parekh, Rajesh ; Honavar, Vasant. / Constructive theory refinement in knowledge based neural networks. IEEE World Congress on Computational Intelligence. editor / Anon. Vol. 3 IEEE, 1998. pp. 2318-2323
@inproceedings{a3b4dff3809649dcaf0a5c1bfedb8ad0,
title = "Constructive theory refinement in knowledge based neural networks",
abstract = "Knowledge based artificial neural networks offer an approach for connectionist theory refinement. We present an algorithm for refining and extending the domain theory incorporated in a knowledge based neural network using constructive neural network learning algorithms. The initial domain theory comprising of propositional rules is translated into a knowledge based network of threshold logic units (threshold neuron). The domain theory is modified by dynamically adding neurons to the existing network. A constructive neural network learning algorithm is used to add and train these additional neurons using a sequence of labeled examples. We propose a novel hybrid constructive learning algorithm based on the Tiling and Pyramid constructive learning algorithms that allows knowledge based neural network to handle patterns with continuous valued attributes. Results of experiments on two non-trivial tasks (the ribosome binding site prediction and the financial advisor) show that our algorithm compares favorably with other algorithms for connectionist theory refinement both in terms of generalization accuracy and network size.",
author = "Rajesh Parekh and Vasant Honavar",
year = "1998",
language = "English (US)",
volume = "3",
pages = "2318--2323",
editor = "Anon",
booktitle = "IEEE World Congress on Computational Intelligence",
publisher = "IEEE",

}

Parekh, R & Honavar, V 1998, Constructive theory refinement in knowledge based neural networks. in Anon (ed.), IEEE World Congress on Computational Intelligence. vol. 3, IEEE, pp. 2318-2323, Proceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3), Anchorage, AK, USA, 5/4/98.

Constructive theory refinement in knowledge based neural networks. / Parekh, Rajesh; Honavar, Vasant.

IEEE World Congress on Computational Intelligence. ed. / Anon. Vol. 3 IEEE, 1998. p. 2318-2323.

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

TY - GEN

T1 - Constructive theory refinement in knowledge based neural networks

AU - Parekh, Rajesh

AU - Honavar, Vasant

PY - 1998

Y1 - 1998

N2 - Knowledge based artificial neural networks offer an approach for connectionist theory refinement. We present an algorithm for refining and extending the domain theory incorporated in a knowledge based neural network using constructive neural network learning algorithms. The initial domain theory comprising of propositional rules is translated into a knowledge based network of threshold logic units (threshold neuron). The domain theory is modified by dynamically adding neurons to the existing network. A constructive neural network learning algorithm is used to add and train these additional neurons using a sequence of labeled examples. We propose a novel hybrid constructive learning algorithm based on the Tiling and Pyramid constructive learning algorithms that allows knowledge based neural network to handle patterns with continuous valued attributes. Results of experiments on two non-trivial tasks (the ribosome binding site prediction and the financial advisor) show that our algorithm compares favorably with other algorithms for connectionist theory refinement both in terms of generalization accuracy and network size.

AB - Knowledge based artificial neural networks offer an approach for connectionist theory refinement. We present an algorithm for refining and extending the domain theory incorporated in a knowledge based neural network using constructive neural network learning algorithms. The initial domain theory comprising of propositional rules is translated into a knowledge based network of threshold logic units (threshold neuron). The domain theory is modified by dynamically adding neurons to the existing network. A constructive neural network learning algorithm is used to add and train these additional neurons using a sequence of labeled examples. We propose a novel hybrid constructive learning algorithm based on the Tiling and Pyramid constructive learning algorithms that allows knowledge based neural network to handle patterns with continuous valued attributes. Results of experiments on two non-trivial tasks (the ribosome binding site prediction and the financial advisor) show that our algorithm compares favorably with other algorithms for connectionist theory refinement both in terms of generalization accuracy and network size.

UR - http://www.scopus.com/inward/record.url?scp=0031630637&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031630637&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0031630637

VL - 3

SP - 2318

EP - 2323

BT - IEEE World Congress on Computational Intelligence

A2 - Anon, null

PB - IEEE

ER -

Parekh R, Honavar V. Constructive theory refinement in knowledge based neural networks. In Anon, editor, IEEE World Congress on Computational Intelligence. Vol. 3. IEEE. 1998. p. 2318-2323