Presentation	1998/5/21 Stochastic Evolution on the Hierarchical Population Koji Sugai,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	This paper proposes a new evolutionary algorithm, hierarchical hillclimbing (HHC), for searching solutions of combinatorial optimization problems. We define hierarchical populations and introduce a new recombination method which is not pair-wise mating. The hierarchical population can maintain the diversity of schemata and make good performance for local searching. The new recombining method make new individuals with probabilities for each bits. And the spurious correlations, which leads the premature convergence, are reduced through recombining of multiple parents. On our simulation, HHC can maintain the competitive schemata and avoid premature convergence through reducing spurious correlations.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	schema disruption / spurious correlation / deceptive problem / hierarchical population / hierarchical hillclimbing
Paper #
Date of Issue

Conference Information
Committee	AI
Conference Date	1998/5/21(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	Artificial Intelligence and Knowledge-Based Processing (AI)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Stochastic Evolution on the Hierarchical Population
Sub Title (in English)
Keyword(1)	schema disruption
Keyword(2)	spurious correlation
Keyword(3)	deceptive problem
Keyword(4)	hierarchical population
Keyword(5)	hierarchical hillclimbing
1st Author's Name	Koji Sugai
1st Author's Affiliation	Fujitsu Aichi Engineering Ltd.()
Date	1998/5/21
Paper #
Volume (vol)	vol.98
Number (no)	58
Page	pp.pp.-
#Pages	8
Date of Issue