[Computer-go] Keynote Lecture by Aja Huang

"Ingo Althöfer" 3-Hirn-Verlag at gmx.de
Tue Jun 21 07:02:27 PDT 2016


Hello,

the organizers in Leiden just informed me:
> We will make a video of the talk and will put it on
> the internet like the lectures of the conference.

I will inform the list when the weblink becomes known.

Ingo.

> Gesendet: Donnerstag, 16. Juni 2016 um 20:15 Uhr
> Von: "David Fotland" <fotland at smart-games.com>
> An: computer-go at computer-go.org
> Betreff: Re: [Computer-go] Keynote Lecture by Aja Huang
>
> Can the lecture be recorded or broadcast for those of us who can’t be there?
> 
> Regards,
> 
> David
> 
> > -----Original Message-----
> > From: Computer-go [mailto:computer-go-bounces at computer-go.org] On
> > Behalf Of "Ingo Althöfer"
> > Sent: Thursday, June 16, 2016 9:36 AM
> > To: computer-go at computer-go.org
> > Subject: [Computer-go] Keynote Lecture by Aja Huang
> > 
> > Hello,
> > 
> > the ICGA is proud to annouce a special talk by Aja Huang during the
> > Computer Olympiad and "Computer Games" conference in Leiden (NL).
> > 
> > **** Computer and Games 2016 Conference ****
> > 
> > Keynote Lecture
> > June 29, 2016: 14.00-15.00 h.
> > 
> > Location: Leiden University, room 1 of the Gorlaeus Building
> > 
> > Lecture by Aja Huang of the AlphaGo team
> > 
> > AlphaGo: Combining Deep Neural Networks with Tree Search
> > 
> > Abstract
> > In this talk we will present the source of power of AlphaGo. In
> > AlphaGo, we use  value networks  to evaluate board positions and
> > policy networks  to select moves. These deep neural networks are
> > trained by a novel combination of supervised learning from human expert
> > games, and reinforcement learning from games of self-play. Without any
> > look ahead search, the neural networks play Go at the level of state-
> > of-the-art Monte Carlo tree search programs that simulate thousands of
> > random games of self-play. We also introduce a new search algorithm
> > that combines Monte Carlo simulation with value and policy networks.
> > Using this search algorithm, our program AlphaGo achieved a 99.8%
> > winning rate against other Go programs, and defeated the human European
> > Go champion by 5 games to 0. In March 2016 AlphaGo defeated Lee Sedol,
> > the strongest human Go player in the last decade.
> > ********************************************************************
> > 
> > Hope, you all will come.
> > 
> > Cheers, Ingo.
> > _______________________________________________
> > Computer-go mailing list
> > Computer-go at computer-go.org
> > http://computer-go.org/mailman/listinfo/computer-go
> 
> _______________________________________________
> Computer-go mailing list
> Computer-go at computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go



More information about the Computer-go mailing list