Performance evaluation of a partial retraining scheme for defective multi-layer neural networks

K. Yamamori, Toru Abe, S. Horiguchi

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

This paper addresses an efficient stuck-defect compensation scheme for multi-layer artificial neural networks implemented in hardware devices. To compensate for stuck defects, we have proposed a two-stage partial retraining scheme that adjusts weights belonging to a neuron affected by defects based on back-propagation (BP) algorithm between two layers. For input neurons, the partial retraining scheme is applied two times; first-stage between the input layer and the hidden layer, second-stage between the hidden layer and the output layer. The partial retraining scheme does not need any additional circuits if the hardware neural network has circuits for learning. In this paper we discuss the performance of the partial retraining scheme, retraining time, network yield and generalization ability. As a result, the partial retraining scheme could compensate the neuron stuck defects about 10 times faster than the whole network retraining by BP algorithm. In addition, yields of networks are also improved. The partial retraining scheme achieved more than 80% recognition ratio for noisy input patterns when 16% neurons of the network have 0-stuck or 1-stuck defects.

本文言語English
ホスト出版物のタイトルProceedings of the Australasian Computer Systems Architecture Conference, ACSAC
出版社IEEE Computer Society
ページ138-145
ページ数8
2001-January
ISBN(印刷版)0769509541
DOI
出版ステータスPublished - 2001
外部発表はい
イベント6th Australasian Computer Systems Architecture Conference, ACSAC 2001 - Gold Coast, Australia
継続期間: 2001 1 292001 1 30

Other

Other6th Australasian Computer Systems Architecture Conference, ACSAC 2001
CountryAustralia
CityGold Coast
Period01/1/2901/1/30

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering

フィンガープリント 「Performance evaluation of a partial retraining scheme for defective multi-layer neural networks」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル