Presentation 1996/12/14
Internal representation analysis from dependencies
Atsuhiro Nada, Naohiro Ishii,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In previous paper, we introduced dependencies to evaluate the extent of the sensitivity of output units to the input units. Such dependencies are calculated from connection weights and thresholds in a lernt neural network. we also introduced another measure, peculiarities, to evaluate the importance of an element in a training vector. In this paper, we study the relationship between dependencies and peculiarities.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) dependency / internal representaion analysis / rule extraction
Paper # NC96-66
Date of Issue

Conference Information
Committee NC
Conference Date 1996/12/14(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Internal representation analysis from dependencies
Sub Title (in English)
Keyword(1) dependency
Keyword(2) internal representaion analysis
Keyword(3) rule extraction
1st Author's Name Atsuhiro Nada
1st Author's Affiliation Department of Information and Computer Engineering,Toyota National College of Technology()
2nd Author's Name Naohiro Ishii
2nd Author's Affiliation Department of Intelligence and Computer Science, Nagoya Institute of Technology
Date 1996/12/14
Paper # NC96-66
Volume (vol) vol.96
Number (no) 430
Page pp.pp.-
#Pages 5
Date of Issue