How an artificial intelligence learnt to play

Last Modified: Tue, Mar 15 2016. 01 12 AM ISTArtificial intelligence sophistication isn’t required past a certain point; it’s essentially a question of crunching numbers Go looks simple, deceptively so. The Chinese board game is played on a board with a grid of 19×19 lines. The object is for two players to alternately place black and white markers on vacant intersections of those lines. The player who “captures” the largest amount of territory wins. And now, this nearly 3,000-year-old board game is a frontier of Artificial Intelligence development. At the time of writing, Google’s DeepMind AI’s AlphaGo program has played four games of a five game series against Go world champion, South Korea’s Lee se-Dol. It lost the fourth, but only after taking the first three and winning the series…


Link to Full Article: How an artificial intelligence learnt to play