Difference between revisions of "Diogo R. Ferreira"
GerdIsenberg (talk | contribs) (Created page with "'''Home * People * Diogo R. Ferreira''' FILE:DiogoRFerreira.jpg|border|right|thumb|link=http://web.ist.utl.pt/diogo.ferreira/| Diogo R. Ferreira <ref>[ht...") |
GerdIsenberg (talk | contribs) |
||
(3 intermediate revisions by the same user not shown) | |||
Line 8: | Line 8: | ||
=Chess Ratings= | =Chess Ratings= | ||
− | In 2010, Diogo R. Ferreira participated on a chess ratings competition <ref>[http://www.kaggle.com/c/chess Chess ratings - Elo versus the Rest of the World - Kaggle]</ref> and made it to 4th place <ref>[http://blog.kaggle.com/2010/11/30/how-i-did-it-diogo-ferreira-on-4th-place-in-elo-chess-ratings-competition/ How I did it: Diogo Ferreira on 4th place in Elo chess ratings competition | no free hunch]</ref> . His approach is based on the [https://en.wikipedia.org/wiki/Pairwise_comparison Bradley-Terry model], but with a slightly different interpretation of what the [[Playing Strength|strength]] of a player is, and with a custom procedure for estimating that strength <ref>[[Diogo R. Ferreira]] ('''2010'''). ''[http://web.ist.utl.pt/diogo.ferreira/chess/ Predicting the Outcome of Chess Games based on Historical Data]''. [https://en.wikipedia.org/wiki/Instituto_Superior_T%C3%A9cnico IST] - [https://en.wikipedia.org/wiki/Technical_University_of_Lisbon Technical University of Lisbon]</ref> . In his [[ICGA Journal]] paper, ''Determining the Strength of Chess Players based on actual Play'' <ref>[[Diogo R. Ferreira]] ('''2012'''). ''Determining the Strength of Chess Players based on actual Play''. [[ICGA Journal#35_1|ICGA Journal, Vol. 35, No. 1]]</ref> , Ferreira elaborates on strength estimation based on a per move basis with the help of a strong chess program and distribution of gain. A gain was defined by the [[Score|score]] difference of [[Houdini|Houdini's 1.5]] fixed depth 20 ply search of all consecutive positions along the game-record, alternating assigned to the player who made the move. Four algorithms for different purposes were defined: | + | In 2010, Diogo R. Ferreira participated on a chess ratings competition offered by [https://en.wikipedia.org/wiki/Kaggle Kaggle] <ref>[http://www.kaggle.com/c/chess Chess ratings - Elo versus the Rest of the World - Kaggle]</ref> and made it to 4th place <ref>[http://blog.kaggle.com/2010/11/30/how-i-did-it-diogo-ferreira-on-4th-place-in-elo-chess-ratings-competition/ How I did it: Diogo Ferreira on 4th place in Elo chess ratings competition | no free hunch]</ref> . His approach is based on the [https://en.wikipedia.org/wiki/Pairwise_comparison Bradley-Terry model], but with a slightly different interpretation of what the [[Playing Strength|strength]] of a player is, and with a custom procedure for estimating that strength <ref>[[Diogo R. Ferreira]] ('''2010'''). ''[http://web.ist.utl.pt/diogo.ferreira/chess/ Predicting the Outcome of Chess Games based on Historical Data]''. [https://en.wikipedia.org/wiki/Instituto_Superior_T%C3%A9cnico IST] - [https://en.wikipedia.org/wiki/Technical_University_of_Lisbon Technical University of Lisbon]</ref> . In his [[ICGA Journal]] paper, ''Determining the Strength of Chess Players based on actual Play'' <ref>[[Diogo R. Ferreira]] ('''2012'''). ''Determining the Strength of Chess Players based on actual Play''. [[ICGA Journal#35_1|ICGA Journal, Vol. 35, No. 1]]</ref> , Ferreira elaborates on strength estimation based on a per move basis with the help of a strong chess program and distribution of gain. A gain was defined by the [[Score|score]] difference of [[Houdini|Houdini's 1.5]] fixed depth 20 ply search of all consecutive positions along the game-record, alternating assigned to the player who made the move. Four algorithms for different purposes were defined: |
# Determine the relative strength between two players i and j. | # Determine the relative strength between two players i and j. | ||
Line 15: | Line 15: | ||
# Determine the strength of a player after a number of moves, based on the rating difference between player and engine, when an estimate of engine strength is available. | # Determine the strength of a player after a number of moves, based on the rating difference between player and engine, when an estimate of engine strength is available. | ||
− | Ratings of various chess players and programs were estimated based on the distribution of gains from various games, [https://en.wikipedia.org/wiki/The_Game_of_the_Century_%28chess%29 The Game of the Century] between [https://en.wikipedia.org/wiki/Donald_Byrne Donald Byrne] and the 13 year old [https://en.wikipedia.org/wiki/Bobby_Fischer Bobby Fischer] was given as sample for algorithm 1 with game score differences, yielding in a rating difference of 113 points in favor to Fischer. The [https://en.wikipedia.org/wiki/London_Chess_Classic#2011_Classic:_3-12_December London Chess Classic 2011] <ref>[http://www.chess.co.uk/twic/chessnews/events/london-chess-classic-2011 London Chess Classic 2011] | [https://en.wikipedia.org/wiki/The_Week_in_Chess The Week in Chess]</ref> <ref>[http://www.chessbase.com/newsdetail.asp?newsid=7754 London R9: Vlad All Over], [[ChessBase|ChessBase News]], December 13, 2011</ref> was used as sample for algorithm 2 and 3, while algorithm 4 was applied for [[Kasparov versus Deep Blue 1997]], which, despite [ | + | Ratings of various chess players and programs were estimated based on the distribution of gains from various games, [https://en.wikipedia.org/wiki/The_Game_of_the_Century_%28chess%29 The Game of the Century] between [https://en.wikipedia.org/wiki/Donald_Byrne Donald Byrne] and the 13 year old [https://en.wikipedia.org/wiki/Bobby_Fischer Bobby Fischer] was given as sample for algorithm 1 with game score differences, yielding in a rating difference of 113 points in favor to Fischer. The [https://en.wikipedia.org/wiki/London_Chess_Classic#2011_Classic:_3-12_December London Chess Classic 2011] <ref>[http://www.chess.co.uk/twic/chessnews/events/london-chess-classic-2011 London Chess Classic 2011] | [https://en.wikipedia.org/wiki/The_Week_in_Chess The Week in Chess]</ref> <ref>[http://www.chessbase.com/newsdetail.asp?newsid=7754 London R9: Vlad All Over], [[ChessBase|ChessBase News]], December 13, 2011</ref> was used as sample for algorithm 2 and 3, while algorithm 4 was applied for [[Kasparov versus Deep Blue 1997]], which, despite [[Garry Kasparov]] lost the match, did result in a higher rating for him - 2754 versus 2741 for [[Deep Blue]]. |
=Selected Publications= | =Selected Publications= | ||
Line 29: | Line 29: | ||
* [[Diogo R. Ferreira]] ('''2012'''). ''[https://ercim-news.ercim.eu/en89/special/performance-analysis-of-healthcare-processes-through-process-mining Performance Analysis of Healthcare Processes through Process Mining]''. [https://dblp.uni-trier.de/db/journals/ercim/ercim2012.html RCIM News 2012] | * [[Diogo R. Ferreira]] ('''2012'''). ''[https://ercim-news.ercim.eu/en89/special/performance-analysis-of-healthcare-processes-through-process-mining Performance Analysis of Healthcare Processes through Process Mining]''. [https://dblp.uni-trier.de/db/journals/ercim/ercim2012.html RCIM News 2012] | ||
* [[Diogo R. Ferreira]] ('''2012'''). ''Determining the Strength of Chess Players based on actual Play''. [[ICGA Journal#35_1|ICGA Journal, Vol. 35, No. 1]] » [[Match Statistics]], [[Houdini]] | * [[Diogo R. Ferreira]] ('''2012'''). ''Determining the Strength of Chess Players based on actual Play''. [[ICGA Journal#35_1|ICGA Journal, Vol. 35, No. 1]] » [[Match Statistics]], [[Houdini]] | ||
− | * [[Diogo R. Ferreira]] ('''2013'''). ''The Impact of the Search Depth on Chess Playing Strength''. [[ICGA Journal#36_2|ICGA Journal, Vol. 36, No. 2]] » [[Depth]], [[Depth#DiminishingReturns|Diminishing Returns]], [[Match Statistics]], [[Houdini]] | + | * <span id="Impact"></span>[[Diogo R. Ferreira]] ('''2013'''). ''The Impact of the Search Depth on Chess Playing Strength''. [[ICGA Journal#36_2|ICGA Journal, Vol. 36, No. 2]] » [[Depth]], [[Depth#DiminishingReturns|Diminishing Returns]], [[Match Statistics]], [[Playing Strength]], [[Houdini]] <ref>[https://www.hiarcs.net/forums/viewtopic.php?t=10004 Ply versus ELO] by Greg, [[Computer Chess Forums|HIARCS Forum]], May 30, 2020</ref> |
* [[Diogo R. Ferreira]], [https://dblp.uni-trier.de/pers/hd/s/Santos:Rui_M= Rui M. Santos] ('''2016'''). ''[https://github.com/diogoff/transition-counting-gpu Parallelization of Transition Counting for Process Mining on Multi-core CPUs and GPUs]''. [https://dblp.uni-trier.de/db/conf/bpm/bpmw2016.html BPM 2016] | * [[Diogo R. Ferreira]], [https://dblp.uni-trier.de/pers/hd/s/Santos:Rui_M= Rui M. Santos] ('''2016'''). ''[https://github.com/diogoff/transition-counting-gpu Parallelization of Transition Counting for Process Mining on Multi-core CPUs and GPUs]''. [https://dblp.uni-trier.de/db/conf/bpm/bpmw2016.html BPM 2016] | ||
* [https://www.researchgate.net/profile/Francisco_Matos3 Francisco A. Matos], [[Diogo R. Ferreira]], [https://www.researchgate.net/profile/P_Carvalho2 Pedro J. Carvalho], [https://en.wikipedia.org/wiki/Joint_European_Torus JET] Contributors ('''2017'''). ''Deep learning for plasma tomography using the bolometer system at JET''. [https://arxiv.org/abs/1701.00322 arXiv:1701.00322] | * [https://www.researchgate.net/profile/Francisco_Matos3 Francisco A. Matos], [[Diogo R. Ferreira]], [https://www.researchgate.net/profile/P_Carvalho2 Pedro J. Carvalho], [https://en.wikipedia.org/wiki/Joint_European_Torus JET] Contributors ('''2017'''). ''Deep learning for plasma tomography using the bolometer system at JET''. [https://arxiv.org/abs/1701.00322 arXiv:1701.00322] |
Latest revision as of 20:01, 10 July 2020
Home * People * Diogo R. Ferreira
Diogo R. Ferreira,
a Portuguese computer scientist and professor of Information systems at Instituto Superior Técnico, Technical University of Lisbon.
His research interests include data science, deep learning, GPU computing, data mining and process mining applied to nuclear fusion, plasma tomography, and disruption prediction [2].
Chess Ratings
In 2010, Diogo R. Ferreira participated on a chess ratings competition offered by Kaggle [3] and made it to 4th place [4] . His approach is based on the Bradley-Terry model, but with a slightly different interpretation of what the strength of a player is, and with a custom procedure for estimating that strength [5] . In his ICGA Journal paper, Determining the Strength of Chess Players based on actual Play [6] , Ferreira elaborates on strength estimation based on a per move basis with the help of a strong chess program and distribution of gain. A gain was defined by the score difference of Houdini's 1.5 fixed depth 20 ply search of all consecutive positions along the game-record, alternating assigned to the player who made the move. Four algorithms for different purposes were defined:
- Determine the relative strength between two players i and j.
- Determine the relative strength of each player i, in terms of a perceived Elo rating r'i for a set of players in a tournament, where the actual Elo ratings ri are known.
- Determine the engine strength based on the rating differences between the engine and a set of players whose Elo ratings and/or perceived ratings are known.
- Determine the strength of a player after a number of moves, based on the rating difference between player and engine, when an estimate of engine strength is available.
Ratings of various chess players and programs were estimated based on the distribution of gains from various games, The Game of the Century between Donald Byrne and the 13 year old Bobby Fischer was given as sample for algorithm 1 with game score differences, yielding in a rating difference of 113 points in favor to Fischer. The London Chess Classic 2011 [7] [8] was used as sample for algorithm 2 and 3, while algorithm 4 was applied for Kasparov versus Deep Blue 1997, which, despite Garry Kasparov lost the match, did result in a higher rating for him - 2754 versus 2741 for Deep Blue.
Selected Publications
2000 ...
- Diogo R. Ferreira (2004). Workflow Management Systems Supporting the Engineering of Business Networks. Ph.D. Thesis
- Diogo R. Ferreira, Daniel Gillblad (2009). Discovering Process Models from Unlabelled Event Logs. BPM 2009
2010 ...
- Michal Walicki, Diogo R. Ferreira (2010). Mining Sequences for Patterns with Non-Repeating Symbols. IEEE Congress on Evolutionary Computation
- Diogo R. Ferreira (2010). Predicting the Outcome of Chess Games based on Historical Data. IST - Technical University of Lisbon
- Michal Walicki, Diogo R. Ferreira (2011). Sequence partitioning for process mining with unlabeled event logs. Data & Knowledge Engineering, Vol. 70, No. 10
- Diogo R. Ferreira (2012). Performance Analysis of Healthcare Processes through Process Mining. RCIM News 2012
- Diogo R. Ferreira (2012). Determining the Strength of Chess Players based on actual Play. ICGA Journal, Vol. 35, No. 1 » Match Statistics, Houdini
- Diogo R. Ferreira (2013). The Impact of the Search Depth on Chess Playing Strength. ICGA Journal, Vol. 36, No. 2 » Depth, Diminishing Returns, Match Statistics, Playing Strength, Houdini [12]
- Diogo R. Ferreira, Rui M. Santos (2016). Parallelization of Transition Counting for Process Mining on Multi-core CPUs and GPUs. BPM 2016
- Francisco A. Matos, Diogo R. Ferreira, Pedro J. Carvalho, JET Contributors (2017). Deep learning for plasma tomography using the bolometer system at JET. arXiv:1701.00322
- Diogo R. Ferreira, Pedro J. Carvalho, Horácio Fernandes, JET Contributors (2018). Full-pulse Tomographic Reconstruction with Deep Neural Networks. arXiv:1802.02242
External Links
- Diogo R. Ferreira | IST - Technical University of Lisbon
- diogoff (Diogo R. Ferreira) · GitHub
- How I did it: Diogo Ferreira on 4th place in Elo chess ratings competition | no free hunch
- Inteview: Discover the Methodology and Mindset of a Kaggle Master, Interview with Diogo R. Ferreira by Jason Brownlee, October 3, 2014
References
- ↑ Diogo R. Ferreira | IST - Technical University of Lisbon
- ↑ Diogo R. Ferreira | IST - Technical University of Lisbon | Research Areas
- ↑ Chess ratings - Elo versus the Rest of the World - Kaggle
- ↑ How I did it: Diogo Ferreira on 4th place in Elo chess ratings competition | no free hunch
- ↑ Diogo R. Ferreira (2010). Predicting the Outcome of Chess Games based on Historical Data. IST - Technical University of Lisbon
- ↑ Diogo R. Ferreira (2012). Determining the Strength of Chess Players based on actual Play. ICGA Journal, Vol. 35, No. 1
- ↑ London Chess Classic 2011 | The Week in Chess
- ↑ London R9: Vlad All Over, ChessBase News, December 13, 2011
- ↑ Diogo R. Ferreira | IST - Technical University of Lisbon | Publications
- ↑ dblp: Diogo R. Ferreira
- ↑ Diogo R. Ferreira - Google Scholar Citations
- ↑ Ply versus ELO by Greg, HIARCS Forum, May 30, 2020