Task-driven Topology Inference for Signal Processing and Learning over Topological Domains

This webinar, presented by Paolo Di Lorenzo from Sapienza University of Rome, explores task-driven topology inference for signal processing and learning over topological domains as part of the Data sciEnce on GrAphS (DEGAS) Webinar Series. The one-hour session, organized in conjunction with the IEEE Signal Processing Society Data Science Initiative, delves into advanced concepts at the intersection of topology, signal processing, and machine learning. Learn about methodologies for inferring optimal topological structures that enhance signal processing tasks and improve learning algorithms when working with data that exists on complex domains. Discover how these techniques can be applied across various fields where understanding the underlying topology of data is crucial for effective analysis and processing.