AlphaGo vs Lee Sedol

[54 sec read]

AlphaGo-Lee-Sedol-game-3-Lee-Sedol-at-press-conference-2

Professional Go payer Lee Sedol

It is a five-game Go match between South Korean professional Go player Lee Sedol and AlphaGo, a computer Go program developed by Google DeepMind, between 9 and 15 March 2016.

result

AlphaGo won the first three, Lee Sedol stroke back to win the fourth and AlphaGo won the final match. So, AlphaGo won the tournament 4-1. AlphaGo is awarded the highest Go grandmaster rank, ninth dan.

a-machine-is-about-to-do-to-cancer-treatment-what-deep-blue-did-to-garry-kasparov-in-chess

IBM Deep Blue vs. Garry Kasparov

Go is a complex board game that requires intuition, creative and strategic thinking.  It has long been considered a difficult challenge in the field of artificial intelligence (AI) and is considerably more difficult to solve than chess. IBM Deep Blue machine beat G. Kasparov in 1997 after the first one was won by Kasparov.

training

General steps in training a deep NN like AlphaGo

12d0004c808f3e42bd1

AlhpaGo Tree Search Technique

AlphaGo is a computer program developed by Google DeepMind to play the board game Go. AlphaGo’s algorithm uses a combination of machine learning and tree search techniques, combined with extensive training, both from human and computer play. The system’s neural networks were initially bootstrapped from human game-play expertise using 30 million moves.

References

Wikipedia

 

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s