A VLSI-based Gaussian kernel mapper for real-time RBF neural networks

Seth Wolpert, M. J. Osborn, M. T. Musavi

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

1 Citation (Scopus)

Abstract

An analog VLSI circuit approach to a radial basis function (RBF) neural network is explored. For each of a number of reference pattern templates, the circuit calculates the Euclidean distance between that template and an unknown point, and maps each distance to a point on the Gaussian surface of that template. Then, these points may either be added in order to form the basis for an RBF approximator or laterally inhibited to form the basis for an RBF classifier. The circuitry for this network has been implemented in 2-micron CMOS technology, and will form the bases for truly parallel and simultaneous standalone neural networks that function in real time without intervention from conventional computers.

Original languageEnglish (US)
Title of host publicationProceedings of the 18th IEEE Annual Northeast Bioengineering Conference, NEBEC 1992
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages51-52
Number of pages2
ISBN (Electronic)0780309022
DOIs
StatePublished - Jan 1 1992
Event18th IEEE Annual Northeast Bioengineering Conference, NEBEC 1992 - Kingston, United States
Duration: Mar 12 1992Mar 13 1992

Publication series

NameProceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC
ISSN (Print)1071-121X
ISSN (Electronic)2160-7001

Conference

Conference18th IEEE Annual Northeast Bioengineering Conference, NEBEC 1992
CountryUnited States
CityKingston
Period3/12/923/13/92

Fingerprint

Neural networks
VLSI circuits
Analog circuits
Classifiers
Networks (circuits)

All Science Journal Classification (ASJC) codes

  • Bioengineering

Cite this

Wolpert, S., Osborn, M. J., & Musavi, M. T. (1992). A VLSI-based Gaussian kernel mapper for real-time RBF neural networks. In Proceedings of the 18th IEEE Annual Northeast Bioengineering Conference, NEBEC 1992 (pp. 51-52). [285918] (Proceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NEBC.1992.285918
Wolpert, Seth ; Osborn, M. J. ; Musavi, M. T. / A VLSI-based Gaussian kernel mapper for real-time RBF neural networks. Proceedings of the 18th IEEE Annual Northeast Bioengineering Conference, NEBEC 1992. Institute of Electrical and Electronics Engineers Inc., 1992. pp. 51-52 (Proceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC).
@inproceedings{7203dae524fc405a823efaaca25db653,
title = "A VLSI-based Gaussian kernel mapper for real-time RBF neural networks",
abstract = "An analog VLSI circuit approach to a radial basis function (RBF) neural network is explored. For each of a number of reference pattern templates, the circuit calculates the Euclidean distance between that template and an unknown point, and maps each distance to a point on the Gaussian surface of that template. Then, these points may either be added in order to form the basis for an RBF approximator or laterally inhibited to form the basis for an RBF classifier. The circuitry for this network has been implemented in 2-micron CMOS technology, and will form the bases for truly parallel and simultaneous standalone neural networks that function in real time without intervention from conventional computers.",
author = "Seth Wolpert and Osborn, {M. J.} and Musavi, {M. T.}",
year = "1992",
month = "1",
day = "1",
doi = "10.1109/NEBC.1992.285918",
language = "English (US)",
series = "Proceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "51--52",
booktitle = "Proceedings of the 18th IEEE Annual Northeast Bioengineering Conference, NEBEC 1992",
address = "United States",

}

Wolpert, S, Osborn, MJ & Musavi, MT 1992, A VLSI-based Gaussian kernel mapper for real-time RBF neural networks. in Proceedings of the 18th IEEE Annual Northeast Bioengineering Conference, NEBEC 1992., 285918, Proceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC, Institute of Electrical and Electronics Engineers Inc., pp. 51-52, 18th IEEE Annual Northeast Bioengineering Conference, NEBEC 1992, Kingston, United States, 3/12/92. https://doi.org/10.1109/NEBC.1992.285918

A VLSI-based Gaussian kernel mapper for real-time RBF neural networks. / Wolpert, Seth; Osborn, M. J.; Musavi, M. T.

Proceedings of the 18th IEEE Annual Northeast Bioengineering Conference, NEBEC 1992. Institute of Electrical and Electronics Engineers Inc., 1992. p. 51-52 285918 (Proceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC).

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

TY - GEN

T1 - A VLSI-based Gaussian kernel mapper for real-time RBF neural networks

AU - Wolpert, Seth

AU - Osborn, M. J.

AU - Musavi, M. T.

PY - 1992/1/1

Y1 - 1992/1/1

N2 - An analog VLSI circuit approach to a radial basis function (RBF) neural network is explored. For each of a number of reference pattern templates, the circuit calculates the Euclidean distance between that template and an unknown point, and maps each distance to a point on the Gaussian surface of that template. Then, these points may either be added in order to form the basis for an RBF approximator or laterally inhibited to form the basis for an RBF classifier. The circuitry for this network has been implemented in 2-micron CMOS technology, and will form the bases for truly parallel and simultaneous standalone neural networks that function in real time without intervention from conventional computers.

AB - An analog VLSI circuit approach to a radial basis function (RBF) neural network is explored. For each of a number of reference pattern templates, the circuit calculates the Euclidean distance between that template and an unknown point, and maps each distance to a point on the Gaussian surface of that template. Then, these points may either be added in order to form the basis for an RBF approximator or laterally inhibited to form the basis for an RBF classifier. The circuitry for this network has been implemented in 2-micron CMOS technology, and will form the bases for truly parallel and simultaneous standalone neural networks that function in real time without intervention from conventional computers.

UR - http://www.scopus.com/inward/record.url?scp=2442503600&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2442503600&partnerID=8YFLogxK

U2 - 10.1109/NEBC.1992.285918

DO - 10.1109/NEBC.1992.285918

M3 - Conference contribution

AN - SCOPUS:2442503600

T3 - Proceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC

SP - 51

EP - 52

BT - Proceedings of the 18th IEEE Annual Northeast Bioengineering Conference, NEBEC 1992

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Wolpert S, Osborn MJ, Musavi MT. A VLSI-based Gaussian kernel mapper for real-time RBF neural networks. In Proceedings of the 18th IEEE Annual Northeast Bioengineering Conference, NEBEC 1992. Institute of Electrical and Electronics Engineers Inc. 1992. p. 51-52. 285918. (Proceedings of the IEEE Annual Northeast Bioengineering Conference, NEBEC). https://doi.org/10.1109/NEBC.1992.285918