Presentation 1996/1/18
A Revision Learner for Expert-Knowledge and Real Examples
Shigeo KANEDA, Hussein ALMUALLIM, Megumi ISHII, Yasuhiro AKIBA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We present a method for learning classification functions from pre-classified examples and a preliminary knowledge provided by experts. The goal is to produce a classification function that has higher accuracy than either the expert knowledge or the classification function inductively learned from the training examples alone. The key idea in our proposed approach is to let the expert knowledge influence the score computations during the process of learning inductively from the training sample. Experimental results are presented demonstrating the power of our approach in a variety of domains.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Machine Learning / Knowledge Acquisition / Expert System
Paper # AI95-44
Date of Issue

Conference Information
Committee AI
Conference Date 1996/1/18(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) A Revision Learner for Expert-Knowledge and Real Examples
Sub Title (in English)
Keyword(1) Machine Learning
Keyword(2) Knowledge Acquisition
Keyword(3) Expert System
1st Author's Name Shigeo KANEDA
1st Author's Affiliation NTT Communication Science Labs()
2nd Author's Name Hussein ALMUALLIM
2nd Author's Affiliation King Fahd University of Petroleum and Minerals
3rd Author's Name Megumi ISHII
3rd Author's Affiliation NTT Communication Science Labs
4th Author's Name Yasuhiro AKIBA
4th Author's Affiliation NTT Communication Science Labs
Date 1996/1/18
Paper # AI95-44
Volume (vol) vol.95
Number (no) 460
Page pp.pp.-
#Pages 8
Date of Issue