BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Graph signal processing for machine learning applications: new ins
 ights and algorithms
DTSTART:20180531T161500
DTSTAMP:20260407T095703Z
UID:25aeb3472701c672599b377fceba5c68bf205ad84d4cd7e8c9cbb562
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Antonio ORTEGA\, University of Southern California (USA)
 \nGraph signal processing (GSP) is an active area of research that seeks t
 o extend to signals defined on irregular graphs tools concepts such as fre
 quency\, filtering and sampling that are well understood for conventional 
 signals defined on regular grids. As an example this leads to the definiti
 on of so called\, graph Fourier transforms (GFTs). In this talk we will pr
 ovide an introduction to basic GSP concepts developed over the last few ye
 ar. Then we will investigate how GSP concepts can allow us to view machine
  learning problems from a different perspective. Specifically\, we will di
 scuss our recent work in three areas:\n\ni) novel GFT designs that can be 
 optimized for different tasks\, such as clustering or spatial data process
 ing\,\nii) a sampling interpretation of semi-supervised learning\, and\nii
 i) a GSP-based analysis of deep learning systems. \n\nBio:  Antonio Orteg
 a received his undergraduate and doctoral degrees from the Universidad Pol
 itecnica de Madrid\, Madrid\, Spain and Columbia University\, New York\, N
 Y\, respectively. In 1994 he joined the Electrical Engineering department 
 at the University of Southern California (USC)\, where he is currently a P
 rofessor and has served as Associate Chair.  He is a Fellow of the IEEE a
 nd EURASIP\, and a member of ACM and APSIPA. He is currently a member of t
 he Board of Governors of the IEEE Signal Processing Society.  He has rece
 ived several paper awards\, including the 2016 Signal Processing Magazine 
 award. His recent research work is focusing on graph signal processing\, m
 achine learning\, multimedia compression and wireless sensor networks.
LOCATION:SV 1717 https://plan.epfl.ch/?room==SV%201717
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR