Signal Processing and Machine Learning on Graphs: A Filter based Perspective.
Ph.D. Mario Coutiño
Mario Coutiño received his M.Sc. and Ph.D. degree (cum laude) in electrical engineering from the Delft University of Technology, Delft, The Netherlands, in July 2016 and April 2021, respectively. Since 2020, he has been a Signal Processing and Machine Learning Researcher with the Netherlands Organisation for Applied Scientific Research (TNO) in the fields of Radar and Sonar sensing. He has held temporally positions with Thales Netherlands, during 2015, and Bang & Olufsen, during 2016. He was Visiting Researcher with RIKEN AIP and with the Digital Technological Center, University of Minnesota, in 2018 and 2019, respectively. His research interests include array and graph signal processing , optimization theory, machine learning and sensing technology. He was recipient of the CONACYT excellence scholarship, of the Best Student Paper Award at IEEE CAMSAP 2017, of the EDA RTI Papers Award 2023, of the NATO SET 318 Best Paper Award and of the IEEE Signal Processing Society Best PhD Dissertation Award 2023.
Keynote talk description:
Graphs are a classical mathematical tool that have been applied to solve various problem in domains ranging from network resource allocation to image processing. In the last decade, the development of extensions of signal processing techniques to data defined on graphs, such as that emanating from social networks, have complemented the well-stablish ideas of spectral graph theory. This has resulted in the consolation of Graph Signal Processing theory for the analysis and manipulation of signals defined on graphs. This talk will explore the fundamentals of graph filters, the workhorse of graph signal processing, and their efficient distributed implementations through applications in signal processing. Additionally, it will discuss how graph filters are applied in machine learning problems through the so-called graph convolutional networks and provide a look to current challenges and opportunities.
