The feat recalled IBM supercomputer Deep Blues 1997 match victory over chess world champion Garry Kasparov.
The Go board consist of a 19 by 19 grid of intersecting lines.
But behind the simple rules lies a game of incredible complexity.
‘Go’ Board
The key to this complexity is Gos branching pattern, Hassabis said.
Until now, the best computer Go programs had played only at the level of human amateurs.
The findings have been published in the journal Nature represent a major coup for machine learning algorithms.
‘Go’ Board
Over time, the policy networks trained the value networks to see how the game was progressing.
This makes AlphaGo search much more humanlike than previous approaches.
Google DeepMind are to be congratulated in developing this impressive piece of software.
source: www.techworm.net
