Difference between revisions of "Yu Nasu"
GerdIsenberg (talk | contribs) |
GerdIsenberg (talk | contribs) |
||
Line 8: | Line 8: | ||
[https://en.wikipedia.org/wiki/Speech_recognition speech recognition] and [https://en.wikipedia.org/wiki/Speech_synthesis speech synthesis] as application of [https://en.wikipedia.org/wiki/Hidden_Markov_model hidden Markov model] and [[Neural Networks|neural networks]] <ref>[https://dblp.org/pers/hd/o/Ohtani:Yamato Yamato Ohtani], [[Yu Nasu]], [https://dblp.org/pers/hd/m/Morita:Masahiro Masahiro Morita], [https://dblp.org/pers/hd/a/Akamine:Masami Masami Akamine] ('''2015'''). ''[https://www.semanticscholar.org/paper/Emotional-transplant-in-statistical-speech-based-on-Ohtani-Nasu/5d6c1846bef6e8f796a84f6d7a381fdcffe1e1dd Emotional transplant in statistical speech synthesis based on emotion additive model]''. [https://dblp.org/db/conf/interspeech/interspeech2015.html#OhtaniNMA15 INTERSPEECH 2015]</ref>. | [https://en.wikipedia.org/wiki/Speech_recognition speech recognition] and [https://en.wikipedia.org/wiki/Speech_synthesis speech synthesis] as application of [https://en.wikipedia.org/wiki/Hidden_Markov_model hidden Markov model] and [[Neural Networks|neural networks]] <ref>[https://dblp.org/pers/hd/o/Ohtani:Yamato Yamato Ohtani], [[Yu Nasu]], [https://dblp.org/pers/hd/m/Morita:Masahiro Masahiro Morita], [https://dblp.org/pers/hd/a/Akamine:Masami Masami Akamine] ('''2015'''). ''[https://www.semanticscholar.org/paper/Emotional-transplant-in-statistical-speech-based-on-Ohtani-Nasu/5d6c1846bef6e8f796a84f6d7a381fdcffe1e1dd Emotional transplant in statistical speech synthesis based on emotion additive model]''. [https://dblp.org/db/conf/interspeech/interspeech2015.html#OhtaniNMA15 INTERSPEECH 2015]</ref>. | ||
− | =Shogi= | + | =[[Shogi]]= |
Along with [[Hisayori Noda]] (Nodchip), [[Jun Okabe]], [[Takahiro Suzuki]], [[Masatoshi Hidaka]], and at times [[Akio Kono]], | Along with [[Hisayori Noda]] (Nodchip), [[Jun Okabe]], [[Takahiro Suzuki]], [[Masatoshi Hidaka]], and at times [[Akio Kono]], | ||
Yu Nasu was member of ''The Minstrel's Ballad: Tanuki's Reign'' | Yu Nasu was member of ''The Minstrel's Ballad: Tanuki's Reign'' | ||
Line 18: | Line 18: | ||
and the [[WCSC29|29th World Computer Shogi Champion]] <ref>[http://www2.computer-shogi.org/wcsc29/ 第29回世界コンピュータ将棋選手権 wcsc29]</ref> [[YaneuraOu]] <ref>[http://yaneuraou.yaneu.com/ やねうら王 公式サイト | コンピューター将棋 やねうら王 公式サイト]</ref> <ref>[https://github.com/yaneurao/YaneuraOu GitHub - yaneurao/YaneuraOu: YaneuraOu is the World's Strongest Shogi engine(AI player), WCSC29 1st winner, educational and USI compliant engine]</ref>. | and the [[WCSC29|29th World Computer Shogi Champion]] <ref>[http://www2.computer-shogi.org/wcsc29/ 第29回世界コンピュータ将棋選手権 wcsc29]</ref> [[YaneuraOu]] <ref>[http://yaneuraou.yaneu.com/ やねうら王 公式サイト | コンピューター将棋 やねうら王 公式サイト]</ref> <ref>[https://github.com/yaneurao/YaneuraOu GitHub - yaneurao/YaneuraOu: YaneuraOu is the World's Strongest Shogi engine(AI player), WCSC29 1st winner, educational and USI compliant engine]</ref>. | ||
− | =NNUE= | + | =[[NNUE]]= |
In 2018, Yu Nasu introduced a new [[Evaluation Function|evaluation function]] based on a shallow [[Neural Networks|neural network]] | In 2018, Yu Nasu introduced a new [[Evaluation Function|evaluation function]] based on a shallow [[Neural Networks|neural network]] | ||
whose heavily overparametrized input layer outputs were [[Incremental Updates|incremental updated]] in [[Make Move|make]] and [[Unmake Move|unmake move]]. | whose heavily overparametrized input layer outputs were [[Incremental Updates|incremental updated]] in [[Make Move|make]] and [[Unmake Move|unmake move]]. |
Revision as of 18:30, 31 July 2020
Yu Nasu, (那須悠)
a Japanese computer scientist and Shogi programmer.
While affiliated with the Tokyo Institute of Technology [1],
and the Knowledge Media Laboratory, Toshiba,
his research focused on natural language processing,
speech recognition and speech synthesis as application of hidden Markov model and neural networks [2].
Shogi
Along with Hisayori Noda (Nodchip), Jun Okabe, Takahiro Suzuki, Masatoshi Hidaka, and at times Akio Kono, Yu Nasu was member of The Minstrel's Ballad: Tanuki's Reign [3] [4] and subsequently is member of the Ziosoft Computer Shogi Club, developing and representing the Shogi playing entities Shouten Gensou Knights of Tanuki [5], the end of genesis T.N.K.evolution turbo type D [6] [7] and the 29th World Computer Shogi Champion [8] YaneuraOu [9] [10].
NNUE
In 2018, Yu Nasu introduced a new evaluation function based on a shallow neural network whose heavily overparametrized input layer outputs were incremental updated in make and unmake move. This approach, dubbed NNUE (ƎUИИ Efficiently Updatable Neural Networks), turned out to become extremely powerful. NNUE was used along with a Stockfish based Shogi adaptation in YaneuraOu, as well in other Shogi playing entities such as Kristallweizen-kai [11], apparently with superhuman AlphaZero strength [12]. YaneuraOu team member Hisayori Noda aka Nodchip proved that Nasu's idea also works well in western chess, yielding to Stockfish NNUE [13].
Selected Publications
- Yu Nasu, Koichi Shinoda, Sadaoki Furu (2011). Cross-Channel Spectral Subtraction for meeting speech recognition. ICASSP 2011
- Ryo Yokoyama, Yu Nasu, Koichi Shinoda, Koji Iwano (2012). Overlapped Speech Detection in Meeting Using Cross-Channel Spectral Subtraction and Spectrum Similarity. INTERSPEECH 2012
- Yamato Ohtani, Yu Nasu, Masahiro Morita, Masami Akamine (2015). Emotional transplant in statistical speech synthesis based on emotion additive model. INTERSPEECH 2015 [15] [16]
- Yu Nasu (2018). ƎUИИ Efficiently Updatable Neural-Network based Evaluation Functions for Computer Shogi. Ziosoft Computer Shogi Club, pdf, pdf (Japanese with English abstract)
External Links
- Yu Nasu's research works | Tokyo Institute of Technology, Tokyo (TITech) and other places, ResearchGate
- やねうら王 公式サイト | コンピューター将棋 やねうら王 公式サイト (YaneuraOu)
- GitHub - yaneurao/YaneuraOu: YaneuraOu is the World's Strongest Shogi engine(AI player), WCSC29 1st winner, educational and USI compliant engine
References
- ↑ Yu Nasu's research works | Tokyo Institute of Technology, Tokyo (TITech) and other places, ResearchGate
- ↑ Yamato Ohtani, Yu Nasu, Masahiro Morita, Masami Akamine (2015). Emotional transplant in statistical speech synthesis based on emotion additive model. INTERSPEECH 2015
- ↑ WCSC26 participation list by Reijer Grimbergen, SHOGI-L, April 08, 2016
- ↑ The 27th World Computer Shogi Championship: participant list by Takenobu Takizawa, SHOGI-L, April 17, 2017
- ↑ 第27回世界コンピュータ将棋選手権 参加チーム
- ↑ 第28回世界コンピュータ将棋選手権 wcsc28
- ↑ Installation instruction of shogi engines, May 28, 2019
- ↑ 第29回世界コンピュータ将棋選手権 wcsc29
- ↑ やねうら王 公式サイト | コンピューター将棋 やねうら王 公式サイト
- ↑ GitHub - yaneurao/YaneuraOu: YaneuraOu is the World's Strongest Shogi engine(AI player), WCSC29 1st winner, educational and USI compliant engine
- ↑ GitHub - Tama4649/Kristallweizen: 第29回世界コンピュータ将棋選手権 準優勝のKristallweizenです。
- ↑ The Stockfish of shogi by Larry Kaufman, CCC, January 07, 2020
- ↑ Stockfish NN release (NNUE) by Henk Drost, CCC, May 31, 2020
- ↑ dblp: Yu Nasu
- ↑ hidden semi-Markov model from Wikipedia
- ↑ Kernel eigenvoice from Wikipedia