Presentation 1998/1/22
Acquisition of a Minimal Instance-Base by Storing Most Prototypical Instances
Yoshitaka Oosugi, Kuniaki Uehara,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In the field of instance-based reasoning, reducing storage cost and computational cost is an important problem. In this paper, we will introduce a new algorithm that constructs a minimal instance-base by storing the most prototypical instance for the classification task. In addition, a small number of near-boundary instances are stored into the instance-base. We empirically show that storage requirements are sharply reduced with small sacrifices in classification accuracy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) case-based reasoning / concept learning / selecting instances / searching / backtracking
Paper # AI97-59
Date of Issue

Conference Information
Committee AI
Conference Date 1998/1/22(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) Acquisition of a Minimal Instance-Base by Storing Most Prototypical Instances
Sub Title (in English)
Keyword(1) case-based reasoning
Keyword(2) concept learning
Keyword(3) selecting instances
Keyword(4) searching
Keyword(5) backtracking
1st Author's Name Yoshitaka Oosugi
1st Author's Affiliation Department of Computer and Systems Engineering, Faculty of Engineering, Kobe University()
2nd Author's Name Kuniaki Uehara
2nd Author's Affiliation Department of Computer and Systems Engineering, Faculty of Engineering, Kobe University:Research Center for Urban Safety and Security, Kobe University
Date 1998/1/22
Paper # AI97-59
Volume (vol) vol.97
Number (no) 498
Page pp.pp.-
#Pages 8
Date of Issue