Presentation	2012-11-26 An approach to estimate the difficulty of Sudoku problems by Neural Network Hideaki AMANO, Isao SASANO, Toru SUGIMOTO,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Sudoku problems are usually classified into several levels according to their difficulties by the authors. People usually use some rules to eliminate candidates to fill in squares, so difficulties are related to the rules. Recently there have been some attempts to calculate the difficulties of Sudoku problems mechanically by the rules used to solve them. Although it is natural to use the rules, there might be some useful rules not discovered yet and moreover there are various ways to calculate the difficulties using some fixed set of rules. In this paper we present an approach to calculate the difficulties by using some neural network where we do not use rules.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Sudoku / Neural Network
Paper #	AI2012-17
Date of Issue

Conference Information
Committee	AI
Conference Date	2012/11/19(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)	An approach to estimate the difficulty of Sudoku problems by Neural Network
Sub Title (in English)
Keyword(1)	Sudoku
Keyword(2)	Neural Network
1st Author's Name	Hideaki AMANO
1st Author's Affiliation	Shibaura Institute of Technology()
2nd Author's Name	Isao SASANO
2nd Author's Affiliation	Shibaura Institute of Technology
3rd Author's Name	Toru SUGIMOTO
3rd Author's Affiliation	Shibaura Institute of Technology
Date	2012-11-26
Paper #	AI2012-17
Volume (vol)	vol.112
Number (no)	319
Page	pp.pp.-
#Pages	6
Date of Issue