Video: What did AlphaGo do to beat the strongest human Go player?

The publishing/video partner of Full Stack Fest was amazingly fast in publishing the video. Kudos to them! So after publishing the slides here goes the video!

If you want to have the slides, here they are ( or via links PDF, Speakerdeck, Slideshare):

In case you want to see it live, the talk will be up again at Codemotion Berlin.

Abstract

This year AlphaGo shocked the  world by decisively beating the strongest human Go player, Lee Sedol. An accomplishment that wasn’t expected for years to come. How did AlphaGo do this? What algorithms did it use? What advances in AI made it possible? This talk will briefly introduce the game of Go, followed by the techniques and algorithms used by AlphaGo to answer these questions.

PS: Yes, Lee Sedol probably wasn’t THE STRONGEST human player – more like Top 3 or Top 5 at the time of the game (most people would probably call Ke Jie the strongest player at the moment). Lee Sedol is the dominant of the last decade though, and when the match was announced nobody on the computer-go mailing list complained about the opponent, so I just assumed he was the strongest or among the strongest but only found out after submitting the talk 🙂 . Plus, sadly “How did AlphaGo beat one of the top 5 Go Players” isn’t as catchy as a title.

Advertisements

Video + Slides: Beating Go Thanks to the Power of Randomness (Rubyconf 2015)

I was happy enough to present at rubyconf this year. Here go my video, slides and abstract!

Video
Slides
Abstract

Go is a board game that is more than 2,500 years old (yes, this is not about the programming language!) and it is fascinating from multiple viewpoints. For instance, go bots still can’t beat professional players, unlike in chess.

This talk will show you what is so special about Go that computers still can’t beat humans. We will take a look at the most popular underlying algorithm and show you how the Monte Carlo method, basically random simulation, plays a vital role in conquering Go’s complexity and creating the strong Go bots of today.