BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Adaptation and learning by networked agents
DTSTART:20161117T091500
DTSTAMP:20260407T105919Z
UID:3e078af032ff47e957a5797a376abd31db9c5623046646c47dfe4df5
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Ali H. Sayed\, UCLA\nNetwork science deals with issues r
 elated to the aggregation\, processing\, and diffusion of information over
  graphs. While interactions among agents can be studied from the perspecti
 ve of cluster formations\, degrees of connectivity\, and small-world effec
 ts\, it is the possibility of having agents interact dynamically with each
  other\, and influence each other's behavior\, that opens up a plethora of
  notable possibilities and challenges.\n\nFor example\, examination of how
  local interactions influence global behavior can lead to a broader unders
 tanding of how localized interactions in the social sciences\, life scienc
 es\, and system sciences influence the evolution of the respective multi-a
 gent networks. In this presentation\, we examine the learning behavior of 
 adaptive networked agents over both strongly and weakly-connected graphs.\
 n\nThe discussion will reveal some interesting patterns of behavior on how
  information flows over graphs. In the strongly-connected case\, all agent
 s are able to learn the desired true state within the same accuracy level\
 , thus attaining a level of “social equilibrium\,” even when the agent
 s are subjected to different noise conditions. In contrast\, in the weakly
 -connected case\, a leader-follower relationship develops with some agents
  dictating the behavior of other agents regardless of the local informatio
 n clues that are sensed by these other agents.\n\nThe findings clarify how
  asymmetries in the exchange of data over graphs can make some agents depe
 ndent on other agents. This scenario arises\, for example\, from intruder 
 attacks by malicious agents\, from the presence of stubborn agents\, or fr
 om failures by critical links. The results have useful implications for th
 e design and operation of multi-agent systems and robotic swarms.​\n\nBi
 o: A. H. Sayed is a distinguished professor and former chairman of electri
 cal engineering at UCLA\, where he leads the UCLA Adaptive Systems Laborat
 ory. An author of over 480 publications and six books\, his research invol
 ves several areas including adaptation and learning theories\, statistical
  inference\, network and data science\, multi-agent systems\, and biologic
 ally-inspired designs.\n\nHis work has been recognized with several awards
  including the 2015 Education Award from the IEEE Signal Processing Societ
 y\, the 2014 Papoulis Award from the European Association for Signal Proce
 ssing\, the 2013 Meritorious Service Award and the 2012 Technical Achievem
 ent Award from the IEEE Signal Processing Society\, the 2005 Terman Award 
 from the American Society for Engineering Education\, and the 2003 Kuwait 
 Prize in Basic Sciences. He has been awarded several Best Paper Awards fro
 m the IEEE\, and is a Fellow of both the IEEE and the American Association
  for the Advancement of Science (AAAS). He is recognized as a Highly Cited
  Researcher by Thomson Reuters. He is currently serving as President-Elect
  of the IEEE Signal Processing Society during the two-year period 2016-201
 7\, followed as President during 2018-2019.​
LOCATION:SV 1717 https://plan.epfl.ch/?room==SV%201717
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR