AllAnalytics - Leo Sadovy - Neural Networks Demystified

You--ve likely heard the news that the Google DeepMind --AlphaGo-- computer not only beat a human expert at the game of Go, defeating the European Go champion, Fan Hui in five straight games, but also beat the reigning world champion grandmaster, South Korea--s Lee Sedol, 4 games to 1. Go is considered to be a significantly more difficult game for a computer to tackle than chess, if only because of the vastly greater number of possible moves over a much larger playing field. Chess has on the order of 1040 possible legal and realistic positions in a 40-move game; Go can have up to 10360, give or take a few tens of orders of magnitude. When Deep Blue beat world chess champion Gary Kasparov back in 1997, it did it with a brute force approach -- a massively parallel computer that would typically search to a depth of between six and eight moves, and up to a maximum of about 20 moves in some situations. It was an expert system (not AI), with separate programing modules/libraries for openings, end games, and middle game strategy and tactic evaluation. All the legal moves and rules had to be programmed into it, and it could not learn as it went (although its programmers made adjustments after each game).