Presentation 2003/3/11
Studies on Effects of Initialization for the Rule Extraction on Structural Learning with Forgetting
Tomokazu MIYAGI, Hiroshi SHIRATSUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This report studies how our proposed initialization effects the rule extraction of neural networks by structural learning with forgetting. This proposed initialization consists of two steps: weights of hidden units are initialized so that their hyperplanes should pass through the center of input pattern set, and those of output units are initialized to zero. From simulation result on descovery of boolean function problem which has 5 and 7 inputs, it was confirmed that proposed initialization gives more simple network structure and higher rule extraction ability from improving the convergence rate towards the optimal structure.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Initialization / structural learning with forgetting / rule extraction / optimal structure
Paper # NC2002-185
Date of Issue

Conference Information
Committee NC
Conference Date 2003/3/11(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) Studies on Effects of Initialization for the Rule Extraction on Structural Learning with Forgetting
Sub Title (in English)
Keyword(1) Initialization
Keyword(2) structural learning with forgetting
Keyword(3) rule extraction
Keyword(4) optimal structure
1st Author's Name Tomokazu MIYAGI
1st Author's Affiliation Graduate School of Engineering and Science, University of the Ryukyus()
2nd Author's Name Hiroshi SHIRATSUCHI
2nd Author's Affiliation Department of Information Engineering, University of the Ryukyus
Date 2003/3/11
Paper # NC2002-185
Volume (vol) vol.102
Number (no) 730
Page pp.pp.-
#Pages 6
Date of Issue