BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv6.5.6//EN
X-ORIGINAL-URL:https://cmc.deusto.eus/
X-WR-CALNAME:cmc.deusto.eus
X-WR-CALDESC:DeustoCCM - Chair of Computational Mathematics at University of Deusto
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-05d9badacfacac78a47cc067c4e90353@cmc.deusto.eus
DTSTART:20221018T154500Z
DTEND:20221018T164500Z
DTSTAMP:20251031T213300Z
CREATED:20251031
LAST-MODIFIED:20251031
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:FAU DCN-AvH Seminar: Natural gradient in evolutionary games
DESCRIPTION:Next Tuesday, October 18, 2022 at 17:45H (Berlin time):\nEvent: FAU DCN-AvH Seminar\nOrganized by: FAU DCN-AvH, Chair for Dynamics, Control and Numerics – Alexander von Humboldt Professorship at FAU, Friedrich-Alexander-Universität Erlangen-Nürnberg (Germany)\nTitle: Natural gradient in evolutionary games\nSpeaker: Prof. Dr. Vladimir Jaćimović\nAffiliation: Faculty of Natural Sciences and Mathematics, University of Montenegro\nWHERE?\nOn-site / online\nOn-site:\nRoom 04.363\nFriedrich-Alexander-Universität Erlangen-Nürnberg\nDepartment Informatik (next to Übungraum 01.254 of Department Mathematik.)\nCauerstraße 11, 91058 Erlangen\nGPS-Koord. Raum: 49.573713N, 11.030428E\nOnline:\nZoom meeting link\nMeeting ID: 614 4658 159 | PIN code: 914397\nAbstract. I will start with a very brief overview of optimization methods. These methods are divided into gradient-based techniques (such as gradient descent) and gradient- free algorithms (stochastic search and evolutionary algorithms).\nIn the second part, I will explain the setup of an evolutionary game and intro- duce replicator equations. Evolutionary Game Theory has been founded in 1970’s as a subfield of Game Theory, inspired by the Darwinian principles. I will demon- strate that evolutionary dynamics can be interpreted a process of collective learning, during which a certain function is maximized over the family of probability distribu- tions. Evolutionary dynamics generate an iterative method for maximization of this objective function. Based on the information-geometric approach to evolutionary dynamics, I answer the following questions:\na) What is the objective that the population during an evolutionary game tends to maximize?\nb) How individuals, by following their simple rules, (unknowingly) contribute to the achievement of this collective objective?\nFinally, we will briefly comment on recent applications of these paradigms and algorithms in Artificial Intelligence.\nThis event on LinkedIn\n
URL:https://cmc.deusto.eus/events-calendar/fau-dcn-avh-seminar-natural-gradient-in-evolutionary-games-2/
ORGANIZER;CN=FAU DCN-AvH:MAILTO:
CATEGORIES:FAU DCN-AvH Seminar,Seminar/Talk
LOCATION:DDS, Friedrich-Alexander-Universität Erlangen-Nürnberg
ATTACH;FMTTYPE=image/png:https://cmc.deusto.eus/wp-content/uploads/FAUDCNAvH-seminar-18oct2022-vladimirJacimovic.png
END:VEVENT
END:VCALENDAR