Difference between revisions of "Giraffe"

From Chessprogramming wiki
Jump to: navigation, search
Line 1: Line 1:
 
'''[[Main Page|Home]] * [[Engines]] * Giraffe'''
 
'''[[Main Page|Home]] * [[Engines]] * Giraffe'''
  
[[FILE:The Burning Giraffe.jpg|border|right|thumb|240px|link=https://en.wikipedia.org/wiki/File:The_Burning_Giraffe.jpg| [[Category:Salvador Dalí]] - [https://en.wikipedia.org/wiki/The_Burning_Giraffe The Burning Giraffe] <ref>[[Category:Salvador Dalí]] - The Burning Giraffe, 1937, [https://en.wikipedia.org/wiki/Oil_painting Oil on panel], [https://en.wikipedia.org/wiki/Kunstmuseum_Basel Kunstmuseum Basel], [https://en.wikipedia.org/wiki/The_Burning_Giraffe The Burning Giraffe from Wikipedia]</ref> ]]  
+
[[FILE:The Burning Giraffe.jpg|border|right|thumb|240px|link=https://en.wikipedia.org/wiki/File:The_Burning_Giraffe.jpg| [[:Category:Salvador Dalí|Salvador Dalí]] - [https://en.wikipedia.org/wiki/The_Burning_Giraffe The Burning Giraffe] <ref>[[:Category:Salvador Dalí|Salvador Dalí]] - The Burning Giraffe, 1937, [https://en.wikipedia.org/wiki/Oil_painting Oil on panel], [https://en.wikipedia.org/wiki/Kunstmuseum_Basel Kunstmuseum Basel], [https://en.wikipedia.org/wiki/The_Burning_Giraffe The Burning Giraffe from Wikipedia]</ref> ]]  
  
 
'''Giraffe''',<br/>
 
'''Giraffe''',<br/>

Revision as of 18:44, 22 September 2018

Home * Engines * Giraffe

Giraffe,
an experimental open source chess engine by Matthew Lai under the GNU General Public License, compliant to the Chess Engine Communication Protocol, written in C++11 and based on deep learning, which is topic of Matthew's master's thesis in August 2015 [2] [3] . Giraffe uses the Eigen linear algebra library [4] , and Pradyumna Kannan's magic move generator [5] [6]. As employee of Google DeepMind, Matthew Lai announced the discontinuation of the Giraffe project in January 2016 [7].

Description

Giraffe's evaluation function is a deep neural network trained by TDLeaf [8] . Its feature representation includes a map of static exchange evaluations for all squares and sides [9] , a structure already proposed by Russell M. Church and Kenneth W. Church in Plans, Goals, and Search Strategies for the Selection of a Move in Chess [10] . Probability-based evaluation scores are not in centipawns nor linear to material , and span a +-10,000 range, with mate scores of +- 30,000. The search recently changed from traditional depth-based iterative deepening to assigning number of nodes (or time) to child nodes [11] . Node budget allocation will also become neural network based.

See also

Publications

Forum Posts

2015

2016

2017...

Re: Is AlphaGo approach unsuitable to chess? by Peter Österlund, CCC, May 31, 2017 » Texel

External Links

Chess Engine

Misc

Giraffe - Internal systems

References

Up one Level