Presentation 2003/12/12
Fault Tolerant Training of Neural Networks for Learning Vector Quantization
Takashi MINOHARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The learning vector quantization(LVQ) is a model of neural networks, and it is used for complex pattern classifications in which typical feedforward networks don't give a good performance. Fault tolerance is an important feature in the neural networks, when they are used for critical application. Many methods for enhancing the fault tolerance of neural networks have been proposed, but most of them are for feedforward networks. There is scarcely any methods for fault tolerance of LVQ neural networks. In this paper, we proposed a dependability measure for the LVQ neural networks, and then we presented two idea, the border emphasis and the encouragement of coupling, to improve the learning algorithm for increasing dependability. The experiment result shows that the proposed algorithm trains networks so that they can achieve high dependability.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural Networks / Learning Vector Quantization / Dependability Measure / Border Emphasis / Encouragement of Coupling
Paper # DC2003-83
Date of Issue

Conference Information
Committee DC
Conference Date 2003/12/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Dependable Computing (DC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Fault Tolerant Training of Neural Networks for Learning Vector Quantization
Sub Title (in English)
Keyword(1) Neural Networks
Keyword(2) Learning Vector Quantization
Keyword(3) Dependability Measure
Keyword(4) Border Emphasis
Keyword(5) Encouragement of Coupling
1st Author's Name Takashi MINOHARA
1st Author's Affiliation Department of Computer Science, Takushoku University()
Date 2003/12/12
Paper # DC2003-83
Volume (vol) vol.103
Number (no) 535
Page pp.pp.-
#Pages 6
Date of Issue