Hi everyone, long time reader, sometimes poster.
I gave a talk last week at Full Stack Fest about Computer Go and the advances that AlphaGo brought (but about MCTS as well of course). It's a 40mins presentation so I had to cut a lot. I think it's a good introduction and the talk was well received, it is more meant for people that know programming but don't know Go, AI or Machine learning (the audience in the conference). Hence, Neural networks are also briefly introduced. Video: https://www.youtube.com/watch?v=b9H9AtbxpPM Post with slides: https://pragtob.wordpress.com/2016/09/15/video-what-did-alphago-do-to-beat-the-strongest-human-go-player/ Maybe it's interesting for people new here or the ones that haven't yet read the AlphaGo paper (and its predecessor). Information is based on many papers, presentations of Aja and this mailing list (of course!). As a corollary, if someone wants to level up on their neural networks skills and enjoy it I can immensely recommend this free online book: http://neuralnetworksanddeeplearning.com/index.html Hope some of you enjoy it, happy for some feedback + thanks for all your interesting conversations! Tobi PS: I know that Lee Sedol doesn't seem to be widely regarded as the strongest human player (Ke Jie is to my understanding), but I don't really follow pro Go that much and on this ML everyone seemed quite satisfied with the choice of Lee Sedol of an opponent so I just assumed it when I submitted the talk. Shame on me :| -- http://www.pragtob.info/ _______________________________________________ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
