Encoding and classification in a model of olfactory cortex

Todd Leen, Max Webb, Steve Rehfuss

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

Abstract

It is observed that the computational model of the olfactory cortex given by J. Ambros-Ingerson et al. (1990) is closely related to multistage vector quantization. Variations of the architecture and learning rules are given. The authors evaluate the performance of the various models applied to encode and classify vowels extracted from spoken letters. The efficacy of neural implementation of multistage and tree-search quantization is demonstrated. For fixed branching ratio it is seen that the tree-search quantizer consistently outperforms the multistage structure, though at considerable resource cost. For networks with equal neural resources, the multistage architecture returns significantly lower MSE than the flat and tree-search architectures. Experiments show that pattern rescaling offers a degree of noise immunity.

Original languageEnglish (US)
Title of host publicationProceedings. IJCNN - International Joint Conference on Neural Networks
Editors Anon
PublisherPubl by IEEE
Pages553-559
Number of pages7
ISBN (Print)0780301641
StatePublished - 1992
Externally publishedYes
EventInternational Joint Conference on Neural Networks - IJCNN-91-Seattle - Seattle, WA, USA
Duration: Jul 8 1991Jul 12 1991

Other

OtherInternational Joint Conference on Neural Networks - IJCNN-91-Seattle
CitySeattle, WA, USA
Period7/8/917/12/91

Fingerprint

Vector quantization
Costs
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Leen, T., Webb, M., & Rehfuss, S. (1992). Encoding and classification in a model of olfactory cortex. In Anon (Ed.), Proceedings. IJCNN - International Joint Conference on Neural Networks (pp. 553-559). Publ by IEEE.

Encoding and classification in a model of olfactory cortex. / Leen, Todd; Webb, Max; Rehfuss, Steve.

Proceedings. IJCNN - International Joint Conference on Neural Networks. ed. / Anon. Publ by IEEE, 1992. p. 553-559.

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

Leen, T, Webb, M & Rehfuss, S 1992, Encoding and classification in a model of olfactory cortex. in Anon (ed.), Proceedings. IJCNN - International Joint Conference on Neural Networks. Publ by IEEE, pp. 553-559, International Joint Conference on Neural Networks - IJCNN-91-Seattle, Seattle, WA, USA, 7/8/91.
Leen T, Webb M, Rehfuss S. Encoding and classification in a model of olfactory cortex. In Anon, editor, Proceedings. IJCNN - International Joint Conference on Neural Networks. Publ by IEEE. 1992. p. 553-559
Leen, Todd ; Webb, Max ; Rehfuss, Steve. / Encoding and classification in a model of olfactory cortex. Proceedings. IJCNN - International Joint Conference on Neural Networks. editor / Anon. Publ by IEEE, 1992. pp. 553-559
@inproceedings{cb1dbea222494681bd470953d8152b27,
title = "Encoding and classification in a model of olfactory cortex",
abstract = "It is observed that the computational model of the olfactory cortex given by J. Ambros-Ingerson et al. (1990) is closely related to multistage vector quantization. Variations of the architecture and learning rules are given. The authors evaluate the performance of the various models applied to encode and classify vowels extracted from spoken letters. The efficacy of neural implementation of multistage and tree-search quantization is demonstrated. For fixed branching ratio it is seen that the tree-search quantizer consistently outperforms the multistage structure, though at considerable resource cost. For networks with equal neural resources, the multistage architecture returns significantly lower MSE than the flat and tree-search architectures. Experiments show that pattern rescaling offers a degree of noise immunity.",
author = "Todd Leen and Max Webb and Steve Rehfuss",
year = "1992",
language = "English (US)",
isbn = "0780301641",
pages = "553--559",
editor = "Anon",
booktitle = "Proceedings. IJCNN - International Joint Conference on Neural Networks",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Encoding and classification in a model of olfactory cortex

AU - Leen, Todd

AU - Webb, Max

AU - Rehfuss, Steve

PY - 1992

Y1 - 1992

N2 - It is observed that the computational model of the olfactory cortex given by J. Ambros-Ingerson et al. (1990) is closely related to multistage vector quantization. Variations of the architecture and learning rules are given. The authors evaluate the performance of the various models applied to encode and classify vowels extracted from spoken letters. The efficacy of neural implementation of multistage and tree-search quantization is demonstrated. For fixed branching ratio it is seen that the tree-search quantizer consistently outperforms the multistage structure, though at considerable resource cost. For networks with equal neural resources, the multistage architecture returns significantly lower MSE than the flat and tree-search architectures. Experiments show that pattern rescaling offers a degree of noise immunity.

AB - It is observed that the computational model of the olfactory cortex given by J. Ambros-Ingerson et al. (1990) is closely related to multistage vector quantization. Variations of the architecture and learning rules are given. The authors evaluate the performance of the various models applied to encode and classify vowels extracted from spoken letters. The efficacy of neural implementation of multistage and tree-search quantization is demonstrated. For fixed branching ratio it is seen that the tree-search quantizer consistently outperforms the multistage structure, though at considerable resource cost. For networks with equal neural resources, the multistage architecture returns significantly lower MSE than the flat and tree-search architectures. Experiments show that pattern rescaling offers a degree of noise immunity.

UR - http://www.scopus.com/inward/record.url?scp=0026732268&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026732268&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780301641

SP - 553

EP - 559

BT - Proceedings. IJCNN - International Joint Conference on Neural Networks

A2 - Anon, null

PB - Publ by IEEE

ER -