BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Quantifying high-order correlations via multivariate extensions of
  the mutual information
DTSTART:20181114T140000
DTEND:20181114T150000
DTSTAMP:20260407T152539Z
UID:fdd384f0d854e3ae3b63800ff6732c027bab6f88a882990e0f0f39fa
CATEGORIES:Conferences - Seminars
DESCRIPTION:Fernando Rosas\n\nFernando Rosas received the B.A. degree in m
 usic composition and philosophy\, the B.Sc. degree in mathematics\, and th
 e M.S. and Ph.D. degrees in engineering sciences from the Pontifícia Univ
 ersidad Católica de Chile. He is currently a Marie Sklodowska-Curie Resea
 rch Fellow in the Department of Mathematics and the Department of Electron
 ic Engineering at Imperial College London. Previously\, he worked as a Pos
 tdoctoral Researcher at the Department of Electrical Engineering of KU Leu
 ven\, and as Research Fellow at the Department of Electrical Engineering o
 f National Taiwan University. His research interests lie in the interface 
 between communication and information theory\, complexity science and comp
 utational neuroscience.\nThe interdependencies that can exist between thre
 e or more variables are often nontrivial\, poorly understood and\, yet\, a
 re paramount for advances in many domains of science. In this talk we pres
 ent an introduction into high-order correlations: statistical dependencies
  that exist between groups of variables that cannot be reduced to pair-wis
 e interactions. For this\, we discuss the most prominent frameworks for co
 mputing these properties from data\, which provide alternative multivariat
 e generalizations of Shannon's mutual information. Moreover\, we introduce
  a new framework that provides an unified perspective over these previousl
 y unrelated approaches\, and develop methods for developing a taxonomy of 
 interdependency structures between three or more variables. We illustrate 
 these ideas on two case studies: cellular automata and Baroque music. Fina
 lly\, we explore implications of these methods to computational neuroscien
 ce\, and discuss future work.\n\nReferences:\n\n[1] F. Rosas\, P.A. Median
 o\, M. Ugarte and H.J. Jensen\, ``An information-theoretic approach to sel
 f-organisation: Emergence of complex interdependencies in coupled dynamica
 l systems''\, in Entropy\, vol. 20 no. 10: 793\, pp.1-25\, Sept. 2018.\nh
 ttps://www.mdpi.com/1099-4300/20/10/793\n\n[2] F. Rosas\, V. Ntranos\, C. 
 J. Ellison\, S. Pollin and M. Verhelst\, ``Understanding Interdependency T
 hrough Complex Information Sharing''\, in Entropy\, vol. 18 no. 2: 38\, pp
 .1-27\, Jan. 2016.\nhttps://www.mdpi.com/1099-4300/18/2/38
LOCATION:INM 202 https://plan.epfl.ch/?room=INM202
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR