Eiji TAKIMOTO


Efficient Sampling Method for Monte Carlo Tree Search Problem
Kazuki TERAOKA Kohei HATANO Eiji TAKIMOTO 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2014/03/01
Vol. E97-D  No. 3  pp. 392-398
Type of Manuscript:  Special Section PAPER (Special Section on Foundations of Computer Science —New Trends in Theory of Computation and Algorithm—)
Category: Computational Learning Theory, Game
Keyword: 
Monte Carlo tree searchrandom samplinggameUCT
 Summary | Full Text:PDF(453.5KB)

Adaptive Online Prediction Using Weighted Windows
Shin-ichi YOSHIDA Kohei HATANO Eiji TAKIMOTO Masayuki TAKEDA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2011/10/01
Vol. E94-D  No. 10  pp. 1917-1923
Type of Manuscript:  Special Section PAPER (Special Section on Information-Based Induction Sciences and Machine Learning)
Category: 
Keyword: 
machine learningdata streamonline learningsliding window
 Summary | Full Text:PDF(526.6KB)

NPN-Representatives of a Set of Optimal Boolean Formulas
Hideaki FUKUHARA Eiji TAKIMOTO Kazuyuki AMANO 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2010/06/01
Vol. E93-A  No. 6  pp. 1008-1015
Type of Manuscript:  Special Section PAPER (Special Section on Discrete Mathematics and Its Applications)
Category: Circuit Complexity
Keyword: 
formula complexityquantum adversary methodsNPN-equivalence classes
 Summary | Full Text:PDF(2.1MB)

Lower Bounds on Quantum Query Complexity for Read-Once Formulas with XOR and MUX Operators
Hideaki FUKUHARA Eiji TAKIMOTO 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/02/01
Vol. E93-D  No. 2  pp. 280-289
Type of Manuscript:  Special Section PAPER (Special Section on Foundations of Computer Science)
Category: 
Keyword: 
quantum query complexityread-once formulasdecision treesadversary method
 Summary | Full Text:PDF(270.1KB)

Online Allocation with Risk Information
Shigeaki HARADA Eiji TAKIMOTO Akira MARUOKA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2006/08/01
Vol. E89-D  No. 8  pp. 2340-2347
Type of Manuscript:  INVITED PAPER (Special Section on Invited Papers from New Horizons in Computing)
Category: 
Keyword: 
online learningresource allocationHedge algorithmaggregating algorithm
 Summary | Full Text:PDF(239.7KB)

Relationships between Horn Formulas and XOR-MDNF Formulas
Kenshi MATSUO Tetsuya KOYAMA Eiji TAKIMOTO Akira MARUOKA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2004/02/01
Vol. E87-D  No. 2  pp. 343-351
Type of Manuscript:  Special Section PAPER (Special Section on Foundations of Computer Science)
Category: 
Keyword: 
XOR-MDNF formulamonotone DNF formulaHorn DNF formuladecision listsincrementally polynomial time
 Summary | Full Text:PDF(311.9KB)

An On-Line Prediction Algorithm Combining Several Prediction Strategies in the Shared Bet Model
Ichiro TAJIKA Eiji TAKIMOTO Akira MARUOKA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1999/02/25
Vol. E82-D  No. 2  pp. 348-355
Type of Manuscript:  PAPER
Category: Algorithm and Computational Complexity
Keyword: 
on-line prediction modelprediction strategymin-max strategyweighted majority algorithm
 Summary | Full Text:PDF(220.1KB)

On the Sample Complexity of Consistent Learning with One-Sided Error
Eiji TAKIMOTO Akira MARUOKA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1995/05/25
Vol. E78-D  No. 5  pp. 518-525
Type of Manuscript:  Special Section PAPER (Special Issue on Algorithmic Learning Theory)
Category: Computational Learning Theory
Keyword: 
computational learning theoryPAC learninglearning with one-sided erroraxis-parallel rectangles
 Summary | Full Text:PDF(617.8KB)

Relationships between PAC-Learning Algorithms and Weak Occam Algorithms
Eiji TAKIMOTO Akira MARUOKA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1992/07/25
Vol. E75-D  No. 4  pp. 442-448
Type of Manuscript:  Special Section PAPER (Special Issue on Algorithmic Learning Theory)
Category: 
Keyword: 
algorithm and computational complexityartificial intelligence and cognitive science
 Summary | Full Text:PDF(623.3KB)