The mathematics behind AlphaGo AI and Google Deepmind

912 Views Asked by At

in case you are following the tech news, Google's AlphaGo beat the world Go champion Lee Sedol, not once but twice.

Here is the link of the game 2 review: http://gogameguru.com/alphago-races-ahead-2-0-lee-sedol/

My friend asked me about how the mathematics is doing works behind AlphaGo's AI. I know it is machine learning, and Google Deepmind uses the term "deep learning", but can't quite elaborate the connection of it with a certain theorem in math. Machine learning is one possible area I would like to pursue in my Mathematics graduate study. Here I appreciate if you guys can tell me a few direction I could follow in the newest mathematics behind this. Thanks.

1

There are 1 best solutions below

1
On

If you are interested in starting your journey in Artificial Intelligence, I suggest to get your hands on Artificial Intelligence: A Modern Approach, by Stuart Russell and Peter Norvig, which comes recommended by the Machine Intelligence Research Institute of San Francisco.

It is a really in-depth introduction to the topic, with very few prerequisites. Plus it has tons of well-thought exercises.