Difference between revisions of "Lev Finkelstein"

From Chessprogramming wiki
Jump to: navigation, search
 
Line 21: Line 21:
 
* [[Lev Finkelstein]], [[Shaul Markovitch]] ('''1998'''). ''Learning to Play Chess Selectively by Acquiring Move Patterns.'' [[ICGA Journal#21_2|ICCA Journal, Vol. 21, No. 2]], [http://www.cs.technion.ac.il/%7Eshaulm/papers/pdf/Finkelstein-Markovitch-icca1998.pdf pdf]
 
* [[Lev Finkelstein]], [[Shaul Markovitch]] ('''1998'''). ''Learning to Play Chess Selectively by Acquiring Move Patterns.'' [[ICGA Journal#21_2|ICCA Journal, Vol. 21, No. 2]], [http://www.cs.technion.ac.il/%7Eshaulm/papers/pdf/Finkelstein-Markovitch-icca1998.pdf pdf]
 
* [[Lev Finkelstein]], [[Shaul Markovitch]] ('''1998'''). ''A Selective Macro-learning Algorithm and its Application to the NxN Sliding-Tile Puzzle''. [https://en.wikipedia.org/wiki/Journal_of_Artificial_Intelligence_Research JAIR], Vol. 8, [https://arxiv.org/abs/cs/9806102 arXiv:cs/9806102]
 
* [[Lev Finkelstein]], [[Shaul Markovitch]] ('''1998'''). ''A Selective Macro-learning Algorithm and its Application to the NxN Sliding-Tile Puzzle''. [https://en.wikipedia.org/wiki/Journal_of_Artificial_Intelligence_Research JAIR], Vol. 8, [https://arxiv.org/abs/cs/9806102 arXiv:cs/9806102]
* [[Lev Finkelstein]], [[Shaul Markovitch]], [https://dblp.uni-trier.de/pers/hd/r/Rivlin:Ehud Ehud Rivlin] ('''2003'''). ''Optimal Schedules for Parallelizing Anytime Algorithms: The Case of Shared Resources''. [https://en.wikipedia.org/wiki/Journal_of_Artificial_Intelligence_Research JAIR], Vol. 19, [https://arxiv.org/abs/1106.5269 arXiv:1106.5269]
+
* [[Lev Finkelstein]], [[Shaul Markovitch]], [[Mathematician#ERivlin|Ehud Rivlin]] ('''2003'''). ''Optimal Schedules for Parallelizing Anytime Algorithms: The Case of Shared Resources''. [https://en.wikipedia.org/wiki/Journal_of_Artificial_Intelligence_Research JAIR], Vol. 19, [https://arxiv.org/abs/1106.5269 arXiv:1106.5269]
 
* [[Lev Finkelstein]] ('''2005'''). ''[http://www.graduate.technion.ac.il/Theses/Abstracts.asp?Id=10988 Offline Scheduling of Anytime Algorithms]''. Ph.D thesis, [https://en.wikipedia.org/wiki/Technion_%E2%80%93_Israel_Institute_of_Technology Technion - Israel Institute of Technology], advisor [[Shaul Markovitch]]  
 
* [[Lev Finkelstein]] ('''2005'''). ''[http://www.graduate.technion.ac.il/Theses/Abstracts.asp?Id=10988 Offline Scheduling of Anytime Algorithms]''. Ph.D thesis, [https://en.wikipedia.org/wiki/Technion_%E2%80%93_Israel_Institute_of_Technology Technion - Israel Institute of Technology], advisor [[Shaul Markovitch]]  
  

Latest revision as of 14:49, 3 July 2020

Home * People * Lev Finkelstein

Lev Finkelstein [1]

Lev Finkelstein,
an Israeli computer scientist and software engineer at Google [2]. He holds a Ph.D. from Technion - Israel Institute of Technology in 2005 under supervision of Shaul Markovitch [3]. His research interests include machine learning, artificial intelligence and anytime algorithms.

Learning to Play Chess Selectively

Lev Finkelstein in his talk Learning to Play Chess Selectively by Acquiring Move Patterns at the Man versus Machine Symposium in 2002 [4]:

Several researchers have noted that human chess players do not perceive a position as a static entity, but as a collection of potential actions. Indeed, it looks as if human chess players are able to follow promising moves without considering all the alternatives. This work studies the possibility of incorporating such capabilities into chess programs.
We present a methodology for representing move patterns.  A movepattern is a structure consisting of a board pattern and a move that can be applied in that pattern. Move patterns are used for selecting promising branches of the search tree, allowing a narrower, and therefore deeper, search. Move patterns are learned during training games and are stored in an hierarchical structure to enable fast retrieval. The talk describes a language for representing move patterns, and methods for learning and using them.
This research was done in collaboration with Shaul Markovitch. 

Selected Publications

[5] [6]

External Links

References

Up one level