Learning algorithms for a neural network with laterally inhibited receptive fields

Qiang Gan; Jun Yao; K. R. Subramanian

Learning algorithms for a neural network with laterally inhibited receptive fields

Qiang Gan^*, Jun Yao, K. R. Subramanian

^*Corresponding author for this work

Physical Therapy and Human Movement Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper presents a neural network with its output layer as a classifier and its hidden layer constrained by laterally inhibited receptive fields as feature extractor, in which the idea that wavelet transforms are very suitable for modeling the primary visual information processing is reflected. Two learning algorithms for designing the receptive fields are proposed. The problem associated with local minima caused by the inherent oscillatory property in laterally inhibited receptive fields is combated in the algorithm using discrete wavelets. Good performance is obtained in the experiment of ECG signal classification using the neural network.

Original language	English (US)
Title of host publication	IEEE World Congress on Computational Intelligence
Editors	Anon
Publisher	IEEE
Pages	1156-1161
Number of pages	6
Volume	2
State	Published - Jan 1 1998
Event	Proceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3) - Anchorage, AK, USA Duration: May 4 1998 → May 9 1998

Other

Other	Proceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3)
City	Anchorage, AK, USA
Period	5/4/98 → 5/9/98

ASJC Scopus subject areas

Software

Cite this

@inproceedings{88d126cc9a4743a187debe0ef246937a,

title = "Learning algorithms for a neural network with laterally inhibited receptive fields",

abstract = "This paper presents a neural network with its output layer as a classifier and its hidden layer constrained by laterally inhibited receptive fields as feature extractor, in which the idea that wavelet transforms are very suitable for modeling the primary visual information processing is reflected. Two learning algorithms for designing the receptive fields are proposed. The problem associated with local minima caused by the inherent oscillatory property in laterally inhibited receptive fields is combated in the algorithm using discrete wavelets. Good performance is obtained in the experiment of ECG signal classification using the neural network.",

author = "Qiang Gan and Jun Yao and Subramanian, {K. R.}",

year = "1998",

month = jan,

day = "1",

language = "English (US)",

volume = "2",

pages = "1156--1161",

editor = "Anon",

booktitle = "IEEE World Congress on Computational Intelligence",

publisher = "IEEE",

note = "Proceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3) ; Conference date: 04-05-1998 Through 09-05-1998",

}

TY - GEN

T1 - Learning algorithms for a neural network with laterally inhibited receptive fields

AU - Gan, Qiang

AU - Yao, Jun

AU - Subramanian, K. R.

PY - 1998/1/1

Y1 - 1998/1/1

N2 - This paper presents a neural network with its output layer as a classifier and its hidden layer constrained by laterally inhibited receptive fields as feature extractor, in which the idea that wavelet transforms are very suitable for modeling the primary visual information processing is reflected. Two learning algorithms for designing the receptive fields are proposed. The problem associated with local minima caused by the inherent oscillatory property in laterally inhibited receptive fields is combated in the algorithm using discrete wavelets. Good performance is obtained in the experiment of ECG signal classification using the neural network.

AB - This paper presents a neural network with its output layer as a classifier and its hidden layer constrained by laterally inhibited receptive fields as feature extractor, in which the idea that wavelet transforms are very suitable for modeling the primary visual information processing is reflected. Two learning algorithms for designing the receptive fields are proposed. The problem associated with local minima caused by the inherent oscillatory property in laterally inhibited receptive fields is combated in the algorithm using discrete wavelets. Good performance is obtained in the experiment of ECG signal classification using the neural network.

UR - http://www.scopus.com/inward/record.url?scp=0031625032&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031625032&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0031625032

VL - 2

SP - 1156

EP - 1161

BT - IEEE World Congress on Computational Intelligence

A2 - Anon, null

PB - IEEE

T2 - Proceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3)

Y2 - 4 May 1998 through 9 May 1998

ER -

Learning algorithms for a neural network with laterally inhibited receptive fields

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this