Skip to Content.
Sympa Menu

fizinfo - [Fizinfo] Machine Learning Techniques in Chess and Go

fizinfo AT


List archive

[Fizinfo] Machine Learning Techniques in Chess and Go

Chronological Thread 
  • From: Gábor Vattay <vattay AT>
  • To: Fizinfo <fizinfo AT>
  • Subject: [Fizinfo] Machine Learning Techniques in Chess and Go
  • Date: Mon, 12 Feb 2018 11:05:42 +0100
  • Authentication-results: (amavisd-new); dkim=pass (2048-bit key)

Kedves Kollégák,

2018 február 20.-án 14:00 órakor az ELTE TTK
Fizikai Intézet, Komplex Rendszerek Fizikája Tanszéken
(1117 Bp. Pázmány P. s. 1/A, 5.128-as szoba)

Fáth Gábor (Morgan Stanley) beszél

"Machine Learning Techniques in Chess and Go"

címmel. Az előadás kivonata:

There have been significant breakthrough developments in Artificial
Intelligence for board games recently. Tabula Rasa Learning for Deep Neural
Networks, combined with Monte Carlo Tree Search, is able to achieve
super-human performance levels in the games of Go and Chess, and surpass
thousands of years of meticulously assembled human knowledge within hours.
Can this be extended to other areas of general interest for humankind? A
great question that remains to be answered in the coming years. In the
talk, we review how recent machine learning techniques are implemented for
board games, how far AI got in this domain, and what lessons the Go and
Chess communities are able to learn from these new developments.

Vattay Gábor

Prof. Gábor Vattay
Department of Physics of Complex Systems
Eötvös University, Budapest
Cell: +36 30 850 2614

  • [Fizinfo] Machine Learning Techniques in Chess and Go, Gábor Vattay, 02/12/2018

Archive powered by MHonArc 2.6.19+.

Top of Page