Unsupervised learning in Gaussian functional neural network

Research output: Contribution to conferencePaper

Abstract

A non-linear neural network model that employs Gaussian-type threshold function is presented. The model is characterized by a probability-natured dataflow in the computing units of the network. It has the ability of learning from unlabeled input signals for pattern classification and functional association. The network consists of two neuron layers: (1) a Gaussian functional net which generates an internal representation of input patterns, and (2) a binary winner-take-all net which provides deterministic output of the network. A significant test approach is applied to the self-organization process of the network. The unsupervised learning scheme employs a bi-variate optimization technique. It tries to minimize the entropy of the network and a two-way complementary criteria function. The network is especially advantageous to the classification of noise-corrupted and incompletely represented stochastic patterns.

Original languageEnglish (US)
Pages515-519
Number of pages5
StatePublished - Dec 1 1990
EventProceedings of the Twenty-First Annual Pittsburgh Conference Part 4 (of 5) - Pittsburgh, PA, USA
Duration: May 3 1990May 4 1990

Other

OtherProceedings of the Twenty-First Annual Pittsburgh Conference Part 4 (of 5)
CityPittsburgh, PA, USA
Period5/3/905/4/90

Fingerprint

Unsupervised learning
Neural networks
Neurons
Pattern recognition
Entropy

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Zhu, Q. (1990). Unsupervised learning in Gaussian functional neural network. 515-519. Paper presented at Proceedings of the Twenty-First Annual Pittsburgh Conference Part 4 (of 5), Pittsburgh, PA, USA, .

Unsupervised learning in Gaussian functional neural network. / Zhu, Qiuming.

1990. 515-519 Paper presented at Proceedings of the Twenty-First Annual Pittsburgh Conference Part 4 (of 5), Pittsburgh, PA, USA, .

Research output: Contribution to conferencePaper

Zhu, Q 1990, 'Unsupervised learning in Gaussian functional neural network' Paper presented at Proceedings of the Twenty-First Annual Pittsburgh Conference Part 4 (of 5), Pittsburgh, PA, USA, 5/3/90 - 5/4/90, pp. 515-519.
Zhu Q. Unsupervised learning in Gaussian functional neural network. 1990. Paper presented at Proceedings of the Twenty-First Annual Pittsburgh Conference Part 4 (of 5), Pittsburgh, PA, USA, .
Zhu, Qiuming. / Unsupervised learning in Gaussian functional neural network. Paper presented at Proceedings of the Twenty-First Annual Pittsburgh Conference Part 4 (of 5), Pittsburgh, PA, USA, .5 p.
@conference{413a71c21a6f42899f6b3abcba6be500,
title = "Unsupervised learning in Gaussian functional neural network",
abstract = "A non-linear neural network model that employs Gaussian-type threshold function is presented. The model is characterized by a probability-natured dataflow in the computing units of the network. It has the ability of learning from unlabeled input signals for pattern classification and functional association. The network consists of two neuron layers: (1) a Gaussian functional net which generates an internal representation of input patterns, and (2) a binary winner-take-all net which provides deterministic output of the network. A significant test approach is applied to the self-organization process of the network. The unsupervised learning scheme employs a bi-variate optimization technique. It tries to minimize the entropy of the network and a two-way complementary criteria function. The network is especially advantageous to the classification of noise-corrupted and incompletely represented stochastic patterns.",
author = "Qiuming Zhu",
year = "1990",
month = "12",
day = "1",
language = "English (US)",
pages = "515--519",
note = "Proceedings of the Twenty-First Annual Pittsburgh Conference Part 4 (of 5) ; Conference date: 03-05-1990 Through 04-05-1990",

}

TY - CONF

T1 - Unsupervised learning in Gaussian functional neural network

AU - Zhu, Qiuming

PY - 1990/12/1

Y1 - 1990/12/1

N2 - A non-linear neural network model that employs Gaussian-type threshold function is presented. The model is characterized by a probability-natured dataflow in the computing units of the network. It has the ability of learning from unlabeled input signals for pattern classification and functional association. The network consists of two neuron layers: (1) a Gaussian functional net which generates an internal representation of input patterns, and (2) a binary winner-take-all net which provides deterministic output of the network. A significant test approach is applied to the self-organization process of the network. The unsupervised learning scheme employs a bi-variate optimization technique. It tries to minimize the entropy of the network and a two-way complementary criteria function. The network is especially advantageous to the classification of noise-corrupted and incompletely represented stochastic patterns.

AB - A non-linear neural network model that employs Gaussian-type threshold function is presented. The model is characterized by a probability-natured dataflow in the computing units of the network. It has the ability of learning from unlabeled input signals for pattern classification and functional association. The network consists of two neuron layers: (1) a Gaussian functional net which generates an internal representation of input patterns, and (2) a binary winner-take-all net which provides deterministic output of the network. A significant test approach is applied to the self-organization process of the network. The unsupervised learning scheme employs a bi-variate optimization technique. It tries to minimize the entropy of the network and a two-way complementary criteria function. The network is especially advantageous to the classification of noise-corrupted and incompletely represented stochastic patterns.

UR - http://www.scopus.com/inward/record.url?scp=0025566501&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025566501&partnerID=8YFLogxK

M3 - Paper

SP - 515

EP - 519

ER -