BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Discrete Mathematics Group - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://dimag.ibs.re.kr
X-WR-CALDESC:Events for Discrete Mathematics Group
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:20200101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20210602T170000
DTEND;TZID=Asia/Seoul:20210602T180000
DTSTAMP:20260420T075044
CREATED:20210506T022454Z
LAST-MODIFIED:20240705T184206Z
UID:4042-1622653200-1622656800@dimag.ibs.re.kr
SUMMARY:Adam Zsolt Wagner\, Constructions in combinatorics via neural networks
DESCRIPTION:Recently\, significant progress has been made in the area of machine learning algorithms\, and they have quickly become some of the most exciting tools in a scientist’s toolbox. In particular\, recent advances in the field of reinforcement learning have led computers to reach superhuman level play in Atari games and Go\, purely through self-play. In this talk\, I will give a very basic introduction to neural networks and reinforcement learning algorithms. I will also indicate how these methods can be adapted to the “game” of trying to find a counterexample to a mathematical conjecture\, and show some examples where this approach was successful.
URL:https://dimag.ibs.re.kr/event/2021-06-02/
LOCATION:Zoom ID: 869 4632 6610 (ibsdimag)
CATEGORIES:Virtual Discrete Math Colloquium
END:VEVENT
END:VCALENDAR