DarkGoCoding project by Joe Redmon is a playable neural network-trained version of the game Go created with open-source framework Darknet:AlphaGo got me interested in game-playing neural networks.
I haven’t actually read their paper yet but I’ve implemented what I imagine is sort of similar to their policy network. It is a neural network that predicts the most likely next moves in a game of Go. You can play along with professional games and see what moves are likely to happen next,invent it play itself, or try to play against it!It will require some coding experience to set up, and but you can find out more here
Source: tumblr.com