Google DeepMind's AlphaGo
Google DeepMind's AlphaGo is a new sensation in the field of artificial intelligence, as many industry experts had predicted that it would take about 10 years to beat human players but AlphaGo's victory against humans has proved them wrong. The main complexity of Go is due to its exhaustive search space: let's say b is game's breadth, and d is its depth, which means the combinations to explore for Go are (b~250, d~150), whereas for chess they are (b~35, d~80). This makes clear the difference in complexity of Go over chess. In fact, IBM Deep Blue beat Garry Kasparov in 1997 using a brute force or exhaustive search technique, which is not possible with the a game of Go.
AlphaGo uses value networks to evaluate the board ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access