Presentation 2001/3/16
Learning of Strongly Correlated Pattern Distribution by Stochastic Feed-Forward Neuralnetworks
Sumiyoshi Fujiki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The learrning ability of the stochastic feed-forward neuralnetwork for the probability distribution of strongly correlated patterns is studied. By using the Kullback's measure the learning process of the inverse XOR problem is studied by the 2-m-2 structure networks with two types of synaptic connections, the one with nearest neighbor interlayer connections only and the other with far neighbor interlayer connections.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Layered Neural Network / Distribution of Strongly Correlated Patterns / iXOR problem
Paper # NC2000-161
Date of Issue

Conference Information
Committee NC
Conference Date 2001/3/16(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) Learning of Strongly Correlated Pattern Distribution by Stochastic Feed-Forward Neuralnetworks
Sub Title (in English)
Keyword(1) Layered Neural Network
Keyword(2) Distribution of Strongly Correlated Patterns
Keyword(3) iXOR problem
1st Author's Name Sumiyoshi Fujiki
1st Author's Affiliation Tohoku Bunka Gakuen University()
Date 2001/3/16
Paper # NC2000-161
Volume (vol) vol.100
Number (no) 688
Page pp.pp.-
#Pages 6
Date of Issue