Matches in SemOpenAlex for { <https://semopenalex.org/work/W2101471689> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W2101471689 endingPage "1528" @default.
- W2101471689 startingPage "1521" @default.
- W2101471689 abstract "Go is an ancient board game that poses unique opportunities and challenges for AI and machine learning. Here we develop a machine learning approach to Go, and related board games, focusing primarily on the problem of learning a good evaluation function in a scalable way. Scalability is essential at multiple levels, from the library of local tactical patterns, to the integration of patterns across the board, to the size of the board itself. The system we propose is capable of automatically learning the propensity of local patterns from a library of games. Propensity and other local tactical information are fed into a recursive neural network, derived from a Bayesian network architecture. The network integrates local information across the board and produces local outputs that represent local territory ownership probabilities. The aggregation of these probabilities provides an effective strategic evaluation function that is an estimate of the expected area at the end (or at other stages) of the game. Local area targets for training can be derived from datasets of human games. A system trained using only 9 × 9 amateur game data performs surprisingly well on a test set derived from 19 × 19 professional game data. Possible directions for further improvements are briefly discussed." @default.
- W2101471689 created "2016-06-24" @default.
- W2101471689 creator A5070587610 @default.
- W2101471689 creator A5088813478 @default.
- W2101471689 date "2007-09-07" @default.
- W2101471689 modified "2023-10-16" @default.
- W2101471689 title "A Scalable Machine Learning Approach to Go" @default.
- W2101471689 cites W150316577 @default.
- W2101471689 cites W1585486615 @default.
- W2101471689 cites W1592486124 @default.
- W2101471689 cites W190065572 @default.
- W2101471689 cites W2122410182 @default.
- W2101471689 cites W2122853437 @default.
- W2101471689 cites W2134912352 @default.
- W2101471689 cites W2152064613 @default.
- W2101471689 cites W2159370375 @default.
- W2101471689 cites W2159920598 @default.
- W2101471689 cites W2164217910 @default.
- W2101471689 cites W61744153 @default.
- W2101471689 doi "https://doi.org/10.7551/mitpress/7503.003.0195" @default.
- W2101471689 hasPublicationYear "2007" @default.
- W2101471689 type Work @default.
- W2101471689 sameAs 2101471689 @default.
- W2101471689 citedByCount "8" @default.
- W2101471689 countsByYear W21014716892012 @default.
- W2101471689 countsByYear W21014716892017 @default.
- W2101471689 countsByYear W21014716892019 @default.
- W2101471689 countsByYear W21014716892021 @default.
- W2101471689 crossrefType "book-chapter" @default.
- W2101471689 hasAuthorship W2101471689A5070587610 @default.
- W2101471689 hasAuthorship W2101471689A5088813478 @default.
- W2101471689 hasConcept C111919701 @default.
- W2101471689 hasConcept C154945302 @default.
- W2101471689 hasConcept C41008148 @default.
- W2101471689 hasConcept C48044578 @default.
- W2101471689 hasConceptScore W2101471689C111919701 @default.
- W2101471689 hasConceptScore W2101471689C154945302 @default.
- W2101471689 hasConceptScore W2101471689C41008148 @default.
- W2101471689 hasConceptScore W2101471689C48044578 @default.
- W2101471689 hasLocation W21014716891 @default.
- W2101471689 hasOpenAccess W2101471689 @default.
- W2101471689 hasPrimaryLocation W21014716891 @default.
- W2101471689 hasRelatedWork W1525643724 @default.
- W2101471689 hasRelatedWork W2067938758 @default.
- W2101471689 hasRelatedWork W2302028273 @default.
- W2101471689 hasRelatedWork W2333420780 @default.
- W2101471689 hasRelatedWork W2364921833 @default.
- W2101471689 hasRelatedWork W2368437561 @default.
- W2101471689 hasRelatedWork W2375199418 @default.
- W2101471689 hasRelatedWork W2382623646 @default.
- W2101471689 hasRelatedWork W2390485179 @default.
- W2101471689 hasRelatedWork W3087771547 @default.
- W2101471689 isParatext "false" @default.
- W2101471689 isRetracted "false" @default.
- W2101471689 magId "2101471689" @default.
- W2101471689 workType "book-chapter" @default.