Difference between revisions of "Kristian Kersting"
GerdIsenberg (talk | contribs) (Created page with "'''Home * People * Kristian Kersting''' FILE:kristianKersting.jpg|border|right|thumb|Kristian Kersting <ref>[https://ml-research.github.io/people/kkerstin...") |
GerdIsenberg (talk | contribs) |
||
| Line 8: | Line 8: | ||
and had appointments at [[Massachusetts Institute of Technology|MIT]], [https://de.wikipedia.org/wiki/Fraunhofer-Institut_f%C3%BCr_Intelligente_Analyse-_und_Informationssysteme Fraunhofer IAIS], [https://en.wikipedia.org/wiki/University_of_Bonn University of Bonn], and [[University of Dortmund|TU Dortmund]]. | and had appointments at [[Massachusetts Institute of Technology|MIT]], [https://de.wikipedia.org/wiki/Fraunhofer-Institut_f%C3%BCr_Intelligente_Analyse-_und_Informationssysteme Fraunhofer IAIS], [https://en.wikipedia.org/wiki/University_of_Bonn University of Bonn], and [[University of Dortmund|TU Dortmund]]. | ||
His main research interests are in [https://en.wikipedia.org/wiki/Statistical_relational_learning statistical relational learning] and [[Artificial Intelligence|artificial intelligence]], and [[Deep Learning|deep learning]]. | His main research interests are in [https://en.wikipedia.org/wiki/Statistical_relational_learning statistical relational learning] and [[Artificial Intelligence|artificial intelligence]], and [[Deep Learning|deep learning]]. | ||
| − | Along with [[Johannes Fürnkranz]], | + | |
| − | the deep learning [[Chess#Variants|chess variant]] engine [[CrazyAra]], which won a five game Crazyhouse online-match versus [https://en.wikipedia.org/wiki/Justin_Tan Justin Tan] aka JannLee with 4-1 | + | =CrazyAra= |
| + | Along with [[Johannes Fürnkranz]] at TU Darmstadt, Kristian Kersting led the ''Deep Learning: Methods and Architectures'' course in 2018, and supported his students [[Johannes Czech]], [[Moritz Willig]] and [[Alena Beyer]] in developing | ||
| + | the deep learning [[Chess#Variants|chess variant]] engine [[CrazyAra]], which won a five game [[Crazyhouse]] online-match versus [https://en.wikipedia.org/wiki/Justin_Tan Justin Tan] aka JannLee with 4-1 | ||
<ref>[https://zhchess.blogspot.com/2018/12/crazyara-plays-jannlee-for-christmas.html Crazyhouse Chess: CrazyAra plays JannLee for Christmas], December 26, 2018</ref> <ref>[https://nachrichten.idw-online.de/2019/02/19/schachmatt-durch-crazyara-kuenstliche-intelligenz-schlaegt-mehrfachen-weltmeister-im-einsetzschach/ Schachmatt durch CrazyAra: Künstliche Intelligenz schlägt mehrfachen Weltmeister im Einsetzschach] by [[Kristian Kersting]], [https://en.wikipedia.org/wiki/Informationsdienst_Wissenschaft Informationsdienst Wissenschaft], February 19, 2019 (German)</ref>. | <ref>[https://zhchess.blogspot.com/2018/12/crazyara-plays-jannlee-for-christmas.html Crazyhouse Chess: CrazyAra plays JannLee for Christmas], December 26, 2018</ref> <ref>[https://nachrichten.idw-online.de/2019/02/19/schachmatt-durch-crazyara-kuenstliche-intelligenz-schlaegt-mehrfachen-weltmeister-im-einsetzschach/ Schachmatt durch CrazyAra: Künstliche Intelligenz schlägt mehrfachen Weltmeister im Einsetzschach] by [[Kristian Kersting]], [https://en.wikipedia.org/wiki/Informationsdienst_Wissenschaft Informationsdienst Wissenschaft], February 19, 2019 (German)</ref>. | ||
| − | Subsequently, he | + | Subsequently, he worked with his students Johannes Czech and [[Patrick Korus]] on an improvement of [[AlphaZero|AlphaZero's]] [[Monte-Carlo Tree Search|MCTS]] / [[Christopher D. Rosin#PUCT|PUCT]] algorithm considering [[Transposition|transpositions]], optionally applied in CrazyAra. |
The proposed '''Monte-Carlo Graph Search''' uses a [https://en.wikipedia.org/wiki/Directed_acyclic_graph directed acyclic graph] (DAG) rather than a [https://en.wikipedia.org/wiki/Tree_structure tree structure] <ref>[[Johannes Czech]], [[Patrick Korus]], [[Kristian Kersting]] ('''2020'''). ''Monte-Carlo Graph Search for AlphaZero''. [https://arxiv.org/abs/2012.11045 arXiv:2012.11045]</ref>. | The proposed '''Monte-Carlo Graph Search''' uses a [https://en.wikipedia.org/wiki/Directed_acyclic_graph directed acyclic graph] (DAG) rather than a [https://en.wikipedia.org/wiki/Tree_structure tree structure] <ref>[[Johannes Czech]], [[Patrick Korus]], [[Kristian Kersting]] ('''2020'''). ''Monte-Carlo Graph Search for AlphaZero''. [https://arxiv.org/abs/2012.11045 arXiv:2012.11045]</ref>. | ||
Revision as of 15:26, 23 May 2021
Home * People * Kristian Kersting
Kristian Kersting [1]
Kristian Kersting,
a German computer scientist and professor at Computer Science Department, TU Darmstadt and head of its Artificial Intelligence and Machine Learning (AIML) lab [2].
He received his Ph.D. from University of Freiburg on inductive logic programming in 2006 under advisor Luc De Raedt,
and had appointments at MIT, Fraunhofer IAIS, University of Bonn, and TU Dortmund.
His main research interests are in statistical relational learning and artificial intelligence, and deep learning.
Contents
CrazyAra
Along with Johannes Fürnkranz at TU Darmstadt, Kristian Kersting led the Deep Learning: Methods and Architectures course in 2018, and supported his students Johannes Czech, Moritz Willig and Alena Beyer in developing the deep learning chess variant engine CrazyAra, which won a five game Crazyhouse online-match versus Justin Tan aka JannLee with 4-1 [3] [4]. Subsequently, he worked with his students Johannes Czech and Patrick Korus on an improvement of AlphaZero's MCTS / PUCT algorithm considering transpositions, optionally applied in CrazyAra. The proposed Monte-Carlo Graph Search uses a directed acyclic graph (DAG) rather than a tree structure [5].
Selected Publications
2000 ...
- Kristian Kersting, Luc De Raedt (2001). Bayesian Logic Programs. arXiv:cs/0111058
- Kristian Kersting, Luc De Raedt (2001). Adaptive Bayesian Logic Programs. ILP 2001
- Kristian Kersting, Luc De Raedt (2001). Towards Combining Inductive Logic Programming with Bayesian Networks. ILP 2001
- Luc De Raedt, Kristian Kersting (2003). Probabilistic logic learning. SIGKDD Explorations, Vol. 5, No. 1, pdf
- Kristian Kersting, Luc De Raedt (2004). Logical Markov Decision Programs and the Convergence of Logical TD(lambda). ILP 2004, pdf
- Luc De Raedt, Kristian Kersting (2004). Probabilistic Inductive Logic Programming. ALT 2004
- Kristian Kersting (2006). An Inductive Logic Programming Approach to Statistical Relational Learning. Frontiers in Artificial Intelligence and Applications, Vol. 148
- Luc De Raedt, Kristian Kersting (2008). Probabilistic Inductive Logic Programming. Lecture Notes in Computer Science, Vol. 4911
2010 ...
- Luc De Raedt, Kristian Kersting (2010, 2017). Statistical Relational Learning. Encyclopedia of Machine Learning and Data Mining, Springer
- Kristian Kersting (2012). Lifted Probabilistic Inference. ECAI 2012, pdf
- Christian Bauckhage, Kristian Kersting (2013). Efficient Information Theoretic Clustering on Discrete Lattices. arXiv:1310.7114
- Christian Bauckhage, Kristian Kersting, Christian Thurau (2014). Künstliche Intelligenz für Computerspiele - Historische Entwicklung und aktuelle Trends. Informatik Spektrum, Vol. 37, No. 6 (German)
- Kristian Kersting (2018). Making AI Smarter. Künstliche Intelligenz, Vol. 32, No. 4
- Kristian Kersting (2018). Machine Learning and Artificial Intelligence: Two Fellow Travelers on the Quest for Intelligent Behavior in Machines. Frontiers in Big Data
- Johannes Czech, Moritz Willig, Alena Beyer, Kristian Kersting, Johannes Fürnkranz (2019). Learning to play the Chess Variant Crazyhouse above World Champion Level with Deep Neural Networks and Human Data. arXiv:1908.06660
2020 ...
- Johannes Czech, Moritz Willig, Alena Beyer, Kristian Kersting, Johannes Fürnkranz (2020). Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data. Frontiers in Artificial Intelligence
- Johannes Czech, Patrick Korus, Kristian Kersting (2020). Monte-Carlo Graph Search for AlphaZero. arXiv:2012.11045
- Kristian Kersting (2020). Rethinking Computer Science Through AI. Künstliche Intelligenz, Vol. 34, No. 4
External Links
- Kristian Kersting – Informatik – Technische Universität Darmstadt
- Kristian Kersting
- Prof. Dr. Kristian Kersting, TU Dortmund
- Kristian Kersting - Google Scholar
- Schachmatt durch CrazyAra: Künstliche Intelligenz schlägt mehrfachen Weltmeister im Einsetzschach by Kristian Kersting, Informationsdienst Wissenschaft, February 19, 2019 (German)
- Sieger des deutschen KI-Preises: Der Traum von der starken KI by Christian Buck, Welt, November 02, 2019
References
- ↑ Kristian Kersting
- ↑ Kristian Kersting
- ↑ Crazyhouse Chess: CrazyAra plays JannLee for Christmas, December 26, 2018
- ↑ Schachmatt durch CrazyAra: Künstliche Intelligenz schlägt mehrfachen Weltmeister im Einsetzschach by Kristian Kersting, Informationsdienst Wissenschaft, February 19, 2019 (German)
- ↑ Johannes Czech, Patrick Korus, Kristian Kersting (2020). Monte-Carlo Graph Search for AlphaZero. arXiv:2012.11045
- ↑ dblp: Kristian Kersting
- ↑ Kristian Kersting - Publication
