Machine Learning

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

| PragTob

A talk about AlphGo and techniques it used with no prior knowledge required. Second talk of the Codemotion Berlin series, mostly the same talk I gave at Full Stack Fest. Something was cut/adjusted. A full recording from the Full Stack Fest version is available here.

You can get the slides via PDF, Speakerdeck and Slideshare.

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.

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

| PragTob

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.

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

| PragTob

I gave this talk at Full Stack Fest (achievement unlocked!) and I practised it before at Strange Group. It’s designed to not really require any previous knowledge (Go, Monte Carlo Tree Search and Neural Networks are all introduced). It was a lot of fun putting together and so far the feedback has also been great.

Additional shout out to the strange group folks who helped cut some content so that I landed perfectly on the 40 minutes mark 🙂

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.

Slides