New neural network architecture based on quadratic function neurons

C. S. Leung; K. F. Cheung; M. C. Poon

New neural network architecture based on quadratic function neurons

C. S. Leung
, K. F. Cheung
, M. C. Poon

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

In this paper, a class of multilayer perceptron known as rotational quadratic function neural networks (RQFNN) will be introduced. The rotational quadratic function neuron (RQFN), the center stage of this class of networks, is a particular implementation of the quadratic function neuron (QFN). Comparing with the traditional implementation, the RQFN requires much less fan-in's and thus much smaller cross-connection volume. The economy of the fan-in's and the cross connection volumes facilitates the mapping of the model onto silicon.

Original language	English
Title of host publication	China 1991 International Conference on Circuits and Systems
Publisher	IEEE
Pages	264-267
ISBN (Print)	780301502
Publication status	Published - 1991
Externally published	Yes
Event	China 1991 International Conference on Circuits and Systems. Part 1 (of 2) - Shenzhen, China Duration: 16 Jun 1991 → 17 Jun 1991

Conference

Conference	China 1991 International Conference on Circuits and Systems. Part 1 (of 2)
City	Shenzhen, China
Period	16/06/91 → 17/06/91

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{af5351cc46134819bbee9c9d0313967b,

title = "New neural network architecture based on quadratic function neurons",

abstract = "In this paper, a class of multilayer perceptron known as rotational quadratic function neural networks (RQFNN) will be introduced. The rotational quadratic function neuron (RQFN), the center stage of this class of networks, is a particular implementation of the quadratic function neuron (QFN). Comparing with the traditional implementation, the RQFN requires much less fan-in's and thus much smaller cross-connection volume. The economy of the fan-in's and the cross connection volumes facilitates the mapping of the model onto silicon.",

author = "Leung, \{C. S.\} and Cheung, \{K. F.\} and Poon, \{M. C.\}",

year = "1991",

language = "English",

isbn = "780301502",

pages = "264--267",

booktitle = "China 1991 International Conference on Circuits and Systems",

publisher = "IEEE",

address = "United States",

note = "China 1991 International Conference on Circuits and Systems. Part 1 (of 2) ; Conference date: 16-06-1991 Through 17-06-1991",

}

TY - GEN

T1 - New neural network architecture based on quadratic function neurons

AU - Leung, C. S.

AU - Cheung, K. F.

AU - Poon, M. C.

PY - 1991

Y1 - 1991

N2 - In this paper, a class of multilayer perceptron known as rotational quadratic function neural networks (RQFNN) will be introduced. The rotational quadratic function neuron (RQFN), the center stage of this class of networks, is a particular implementation of the quadratic function neuron (QFN). Comparing with the traditional implementation, the RQFN requires much less fan-in's and thus much smaller cross-connection volume. The economy of the fan-in's and the cross connection volumes facilitates the mapping of the model onto silicon.

AB - In this paper, a class of multilayer perceptron known as rotational quadratic function neural networks (RQFNN) will be introduced. The rotational quadratic function neuron (RQFN), the center stage of this class of networks, is a particular implementation of the quadratic function neuron (QFN). Comparing with the traditional implementation, the RQFN requires much less fan-in's and thus much smaller cross-connection volume. The economy of the fan-in's and the cross connection volumes facilitates the mapping of the model onto silicon.

UR - https://www.scopus.com/pages/publications/0026284905

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0026284905&origin=recordpage

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 780301502

SP - 264

EP - 267

BT - China 1991 International Conference on Circuits and Systems

PB - IEEE

T2 - China 1991 International Conference on Circuits and Systems. Part 1 (of 2)

Y2 - 16 June 1991 through 17 June 1991

ER -

New neural network architecture based on quadratic function neurons

Abstract

Conference

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this