Presentation 1998/11/17
Transformation of unlearning ability in neural networks to simulated annealing algorithm.
Takatoshi Sakaue, Yoshihide Tamori, Ryoji Suzuki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Concerning a learning algorithm which stores patterns and their complmentary components to decraese probability of converging spurious memories, we studied how the complementary components work to decrease the probability. The learning algorithm is compared to unlearning ability of controlling temperature in simulated annealing. And the complementary components are converted into pseudo temperature of neural networks.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Unlearning / Spurious memories / Simulated annealing / Complementaly components
Paper # NC98-62
Date of Issue

Conference Information
Committee NC
Conference Date 1998/11/17(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) Transformation of unlearning ability in neural networks to simulated annealing algorithm.
Sub Title (in English)
Keyword(1) Unlearning
Keyword(2) Spurious memories
Keyword(3) Simulated annealing
Keyword(4) Complementaly components
1st Author's Name Takatoshi Sakaue
1st Author's Affiliation Human Information Systems Laboratories, KIT()
2nd Author's Name Yoshihide Tamori
2nd Author's Affiliation Human Information Systems Laboratories, KIT
3rd Author's Name Ryoji Suzuki
3rd Author's Affiliation Human Information Systems Laboratories, KIT
Date 1998/11/17
Paper # NC98-62
Volume (vol) vol.98
Number (no) 401
Page pp.pp.-
#Pages 5
Date of Issue