A pattern recognition neural network using many sets of weights and biases

Dung Le, Makoto Mizukawa

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

4 Citations (Scopus)

Abstract

In supervised training, we often try to find out a set of weights and biases for a pattern recognition neural network in order to classify all patterns in a training data set. However, it would be difficult if the neural network was not big enough for learning a large training data set. In this paper, we propose a training method and a design of pattern recognition neural network that is not big but still able to classify all the training patterns exactly. The neural network is designed with a reject output to separate the training data set into some parts for classifying more easily. The training method helps the neural network to find out not only one but many sets of weights and biases for classifying all the training patterns, controlling the recognizing rejection and reducing the error rate. On the other hand, with this design we can reduce the size of the neural network implemented on a FPGA chip in order to make fast smart sensors for the robots.

Original languageEnglish
Title of host publicationProceedings of the 2007 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2007
Pages285-290
Number of pages6
DOIs
Publication statusPublished - 2007
Event2007 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2007 - Jacksonville, FL
Duration: 2007 Jun 202007 Jun 23

Other

Other2007 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2007
CityJacksonville, FL
Period07/6/2007/6/23

Fingerprint

Pattern recognition
Neural networks
Smart sensors
Field programmable gate arrays (FPGA)
Robots

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Le, D., & Mizukawa, M. (2007). A pattern recognition neural network using many sets of weights and biases. In Proceedings of the 2007 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2007 (pp. 285-290). [4269856] https://doi.org/10.1109/CIRA.2007.382856

A pattern recognition neural network using many sets of weights and biases. / Le, Dung; Mizukawa, Makoto.

Proceedings of the 2007 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2007. 2007. p. 285-290 4269856.

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

Le, D & Mizukawa, M 2007, A pattern recognition neural network using many sets of weights and biases. in Proceedings of the 2007 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2007., 4269856, pp. 285-290, 2007 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2007, Jacksonville, FL, 07/6/20. https://doi.org/10.1109/CIRA.2007.382856
Le D, Mizukawa M. A pattern recognition neural network using many sets of weights and biases. In Proceedings of the 2007 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2007. 2007. p. 285-290. 4269856 https://doi.org/10.1109/CIRA.2007.382856
Le, Dung ; Mizukawa, Makoto. / A pattern recognition neural network using many sets of weights and biases. Proceedings of the 2007 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2007. 2007. pp. 285-290
@inproceedings{6339b10868424f34ad075bf43e1d8603,
title = "A pattern recognition neural network using many sets of weights and biases",
abstract = "In supervised training, we often try to find out a set of weights and biases for a pattern recognition neural network in order to classify all patterns in a training data set. However, it would be difficult if the neural network was not big enough for learning a large training data set. In this paper, we propose a training method and a design of pattern recognition neural network that is not big but still able to classify all the training patterns exactly. The neural network is designed with a reject output to separate the training data set into some parts for classifying more easily. The training method helps the neural network to find out not only one but many sets of weights and biases for classifying all the training patterns, controlling the recognizing rejection and reducing the error rate. On the other hand, with this design we can reduce the size of the neural network implemented on a FPGA chip in order to make fast smart sensors for the robots.",
author = "Dung Le and Makoto Mizukawa",
year = "2007",
doi = "10.1109/CIRA.2007.382856",
language = "English",
isbn = "1424407907",
pages = "285--290",
booktitle = "Proceedings of the 2007 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2007",

}

TY - GEN

T1 - A pattern recognition neural network using many sets of weights and biases

AU - Le, Dung

AU - Mizukawa, Makoto

PY - 2007

Y1 - 2007

N2 - In supervised training, we often try to find out a set of weights and biases for a pattern recognition neural network in order to classify all patterns in a training data set. However, it would be difficult if the neural network was not big enough for learning a large training data set. In this paper, we propose a training method and a design of pattern recognition neural network that is not big but still able to classify all the training patterns exactly. The neural network is designed with a reject output to separate the training data set into some parts for classifying more easily. The training method helps the neural network to find out not only one but many sets of weights and biases for classifying all the training patterns, controlling the recognizing rejection and reducing the error rate. On the other hand, with this design we can reduce the size of the neural network implemented on a FPGA chip in order to make fast smart sensors for the robots.

AB - In supervised training, we often try to find out a set of weights and biases for a pattern recognition neural network in order to classify all patterns in a training data set. However, it would be difficult if the neural network was not big enough for learning a large training data set. In this paper, we propose a training method and a design of pattern recognition neural network that is not big but still able to classify all the training patterns exactly. The neural network is designed with a reject output to separate the training data set into some parts for classifying more easily. The training method helps the neural network to find out not only one but many sets of weights and biases for classifying all the training patterns, controlling the recognizing rejection and reducing the error rate. On the other hand, with this design we can reduce the size of the neural network implemented on a FPGA chip in order to make fast smart sensors for the robots.

UR - http://www.scopus.com/inward/record.url?scp=34948816680&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34948816680&partnerID=8YFLogxK

U2 - 10.1109/CIRA.2007.382856

DO - 10.1109/CIRA.2007.382856

M3 - Conference contribution

AN - SCOPUS:34948816680

SN - 1424407907

SN - 9781424407903

SP - 285

EP - 290

BT - Proceedings of the 2007 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2007

ER -