An FPGA Implementation of Finite Physical Quantity Neural Network

Takashi Sotohebo; Minoru Watanabe; Funtinori Kobayashi

doi:10.20965/jrm.2003.p0136

single-rb.php

« previous

JRM Vol.15 No.2 pp. 136-142

doi: 10.20965/jrm.2003.p0136

(2003)

Paper:

Views over last 60 days: 377

An FPGA Implementation of Finite Physical Quantity Neural Network

Takashi Sotohebo, Minoru Watanabe, and Funtinori Kobayashi

Faculty of Information, Department of Control Engineering and Computer Science, Kyushyu Institute of Technology, 680-4 Kawazu, Iizuka, 829-8502 Japan

Received:

October 24, 2002

Accepted:

February 10, 2003

Published:

April 20, 2003

Keywords:

FPGAs, neural networks, self-organization

Abstract

We propose installing a finite physical quantity neural network model on a high-density field programmable gate array (FPGA) at high speed by reducing multipliers. We could thereby downsize circuits without loss of precision. We evaluated its installation and experimental results for image recognition.

Cite this article as:

T. Sotohebo, M. Watanabe, and F. Kobayashi, “An FPGA Implementation of Finite Physical Quantity Neural Network,” J. Robot. Mechatron., Vol.15 No.2, pp. 136-142, 2003.

Data files:

This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.