Matches in SemOpenAlex for { <https://semopenalex.org/work/W1608320786> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W1608320786 abstract "The oriental game of Go is increasingly recognized as the grand challenge of Artificial Intelligence (AI). So far, traditional AI approaches have resulted in programs that play at the level of a human amateur. Engineering Go knowledge into a Go playing program has proven to be a difficult task, a machine learning approach might therefore be successful. In this study, a supervised learning approach is used to learn to distinguish good moves from bad moves. This is done by training a neural network on a database of moves played by human players. The network's performance is measured on a prediction task. Three main research directions can be identified in this study. The first direction relates to the features used to encode a position in the game of Go. Specifically, an attempt is made to capture global information into a local area. The second research direction addresses the methodology of supervised learning. In order to gain some insight in the ability of a neural network to extract the knowledge used by human experts, both professional and human amateur games are used in the training process. Furthermore, games used in the training sets are decomposed to test whether knowledge obtained in a specific part of the game can be applied to the entire game. The last research direction is an attempt to uncover the relation between move prediction accuracy and playing strength. Results show that (1) capturing global information leads to a significantly higher prediction performance, (2) professional games do not necessarily provide a better base for achieving a high prediction score than amateur games, (3) knowledge obtained from one part of the game does not generalize over the entire game, and (4) no strong claims can be made regarding the relation between prediction accuracy and playing strength, at least for the program used in this study." @default.
- W1608320786 created "2016-06-24" @default.
- W1608320786 creator A5053859724 @default.
- W1608320786 date "2005-04-29" @default.
- W1608320786 modified "2023-09-27" @default.
- W1608320786 title "Machine Learning in Go: Supervised Learning in Move Prediction" @default.
- W1608320786 cites W131751472 @default.
- W1608320786 cites W1487001863 @default.
- W1608320786 cites W1492505991 @default.
- W1608320786 cites W1499385817 @default.
- W1608320786 cites W1556191380 @default.
- W1608320786 cites W1598695809 @default.
- W1608320786 cites W1608067766 @default.
- W1608320786 cites W1809077948 @default.
- W1608320786 cites W2100097207 @default.
- W1608320786 cites W2111935653 @default.
- W1608320786 cites W2127088021 @default.
- W1608320786 cites W2138289776 @default.
- W1608320786 cites W2138317061 @default.
- W1608320786 cites W2143908786 @default.
- W1608320786 cites W2148544875 @default.
- W1608320786 cites W2157014441 @default.
- W1608320786 cites W2160276617 @default.
- W1608320786 cites W2167303412 @default.
- W1608320786 cites W2169803171 @default.
- W1608320786 cites W2186453176 @default.
- W1608320786 cites W2336778893 @default.
- W1608320786 cites W2525796107 @default.
- W1608320786 cites W2913764096 @default.
- W1608320786 hasPublicationYear "2005" @default.
- W1608320786 type Work @default.
- W1608320786 sameAs 1608320786 @default.
- W1608320786 citedByCount "0" @default.
- W1608320786 crossrefType "journal-article" @default.
- W1608320786 hasAuthorship W1608320786A5053859724 @default.
- W1608320786 hasConcept C111919701 @default.
- W1608320786 hasConcept C119857082 @default.
- W1608320786 hasConcept C124101348 @default.
- W1608320786 hasConcept C127413603 @default.
- W1608320786 hasConcept C136389625 @default.
- W1608320786 hasConcept C154945302 @default.
- W1608320786 hasConcept C17744445 @default.
- W1608320786 hasConcept C199539241 @default.
- W1608320786 hasConcept C201995342 @default.
- W1608320786 hasConcept C25343380 @default.
- W1608320786 hasConcept C2778044066 @default.
- W1608320786 hasConcept C2780451532 @default.
- W1608320786 hasConcept C41008148 @default.
- W1608320786 hasConcept C50644808 @default.
- W1608320786 hasConcept C98045186 @default.
- W1608320786 hasConceptScore W1608320786C111919701 @default.
- W1608320786 hasConceptScore W1608320786C119857082 @default.
- W1608320786 hasConceptScore W1608320786C124101348 @default.
- W1608320786 hasConceptScore W1608320786C127413603 @default.
- W1608320786 hasConceptScore W1608320786C136389625 @default.
- W1608320786 hasConceptScore W1608320786C154945302 @default.
- W1608320786 hasConceptScore W1608320786C17744445 @default.
- W1608320786 hasConceptScore W1608320786C199539241 @default.
- W1608320786 hasConceptScore W1608320786C201995342 @default.
- W1608320786 hasConceptScore W1608320786C25343380 @default.
- W1608320786 hasConceptScore W1608320786C2778044066 @default.
- W1608320786 hasConceptScore W1608320786C2780451532 @default.
- W1608320786 hasConceptScore W1608320786C41008148 @default.
- W1608320786 hasConceptScore W1608320786C50644808 @default.
- W1608320786 hasConceptScore W1608320786C98045186 @default.
- W1608320786 hasLocation W16083207861 @default.
- W1608320786 hasOpenAccess W1608320786 @default.
- W1608320786 hasPrimaryLocation W16083207861 @default.
- W1608320786 hasRelatedWork W100755831 @default.
- W1608320786 hasRelatedWork W1778554682 @default.
- W1608320786 hasRelatedWork W183409260 @default.
- W1608320786 hasRelatedWork W1969743814 @default.
- W1608320786 hasRelatedWork W2057066360 @default.
- W1608320786 hasRelatedWork W2094329841 @default.
- W1608320786 hasRelatedWork W2099645052 @default.
- W1608320786 hasRelatedWork W2135129960 @default.
- W1608320786 hasRelatedWork W2184654423 @default.
- W1608320786 hasRelatedWork W2257979135 @default.
- W1608320786 hasRelatedWork W2304908218 @default.
- W1608320786 hasRelatedWork W23427608 @default.
- W1608320786 hasRelatedWork W2543678130 @default.
- W1608320786 hasRelatedWork W2945260500 @default.
- W1608320786 hasRelatedWork W2998029079 @default.
- W1608320786 hasRelatedWork W3100038332 @default.
- W1608320786 hasRelatedWork W3100681408 @default.
- W1608320786 hasRelatedWork W3176824115 @default.
- W1608320786 hasRelatedWork W3208786560 @default.
- W1608320786 hasRelatedWork W940504451 @default.
- W1608320786 isParatext "false" @default.
- W1608320786 isRetracted "false" @default.
- W1608320786 magId "1608320786" @default.
- W1608320786 workType "article" @default.