Talk by Prof. Antonio Ortega (University of Southern California, USA)

Title:
Graph Signal Processing for Machine Learning Applications: New Insights and Algorithms

Speaker:
Prof. Antonio Ortega (University of Southern California, USA)

Abstract:
Graph signal processing (GSP) is an active area of research that seeks to extend to signals defined on irregular graphs tools concepts such as frequency, filtering and sampling that are well understood for conventional signals defined on regular grids. As an example this leads to the definition of so called, graph Fourier transforms (GFTs). In this talk we will provide an introduction to basic GSP concepts developed over the last few year. Then we will investigate how GSP concepts can allow us to view machine learning problems from a different perspective. Specifically, we will discuss our recent work in three area: i) novel GFT designs that can be optimized for different tasks, such as clustering or spatial data processing, ii) a sampling interpretation of semi-supervised learning, and iii) a GSP-based analysis of deep learning systems.