# jemdoc: addcss{rbh.css}, addcss{jacob.css} = prologue ~ AlphaGo, the end of an era ~~~ - end of era: human go supremacy - try to watch [https://www.alphagomovie.com/ alphago movie] - 2006 start of computer go revolution -- MCTS, Crazystone ~ [http://www.remi-coulom.fr/CG2006/CG2006.pdf Coulom] -- UCB, UCT ~ [http://www.sztaki.hu/~szcsaba/papers/ecml06.pdf Kocsis\+Szepesvari] -- UCT, patterns, MoGo ~ [https://hal.inria.fr/inria-00117266v3/document Gelly\+Wang\+Munos\+Teytaud] -- [http://mcts.ai:80/index.html MCTS explained] - [https://en.wikipedia.org/wiki/Go_ranks_and_ratings\#Kyu_and_dan_ranks go ranking system] - 2015, top Go programs Zen, Crazystone, about 8dan -- 2014 Crazystone + 4 stones defeats Norimota Yoda by 2.5 points -- weaker than top amateur -- weaker than any pro (around [http://lifein19x19.com/forum/viewtopic.php?f=13&t=580 1200] go pros) - boom -- 2016 Jan 28 [https://storage.googleapis.com/deepmind-media/alphago/AlphaGoNaturePaper.pdf AlphaGo Nature paper] -- 2015 Oct AlphaGo v [https://en.wikipedia.org/wiki/Fan_Hui Fan Hui] 5-0 -- AG to play Lee Sedol March 2016 Seoul - AG-LS pre-game predictions -- AG-FH match: many AG moves sub-optimal, throwing away points -- top pro should easily beat this version of AG -- so LS will win ? - but some sub-optimal moves were not errors -- AG picks move that maximizes est. win-prob, not est. win-score, - and ... between matches -- AG algorithm changed -- AG NNs trained non-stop (and improved) - 2016 Mar [https://en.wikipedia.org/wiki/AlphaGo_versus_Lee_Sedol AG v Sedol] 4-1 -- game 1, LS tries unususal early moves to throw AG off its game, fails -- 10 Mar game 2 [https://www.youtube.com/watch?v=HT-UZkiOLv8 move 37] ~ to me, era ends here (commentary [https://en.wikipedia.org/wiki/Michael_Redmond_(Go_player) Michael Redmond]) -- more on [http://webdocs.cs.ualberta.ca/~hayward/670gga/jem/go.html AG-Sedol and computer go] - how does AlphaGo work ? - in this course, we explore basic algorithms for solving puzzles and games - general algorithmic principles: ~ search, knowledge, simulations - by the end of the course you will learn most of the ideas behind AlphaGo - missing pieces (image recognition via deep convolution neural nets) in CMPUT 496 - DCNN (not covered in this course) -- [https://en.wikipedia.org/wiki/Convolutional_neural_network wiki CNN] -- [https://en.wikipedia.org/wiki/Deep_learning wiki deep learning] -- [http://neuralnetworksanddeeplearning.com/ Nielsen NN and DL] -- [http://www.deeplearningbook.org/ Goodfellow\+Bengio\+Courville DL] -- [http://colah.github.io/ Chris Olah's blog] ~~~