Numerous phenomena in real-world data require a multi-scale perspective. Often, there is not just one single scale that is sufficient to faithfully represent a data set. Shifting from an ‘either–or’ selection of relevant scales to a ‘both–and’ utilization of all scales results in novel insights and improved expressive power.
Topological data analysis has recently emerged as an effective tool for obtaining such multi-scale perspectives of real-world data sets. This talk will focus on learning appropriate topological representations for structured and unstructured data sets, with a particular focus on applications in the life sciences.
Bastian Rieck is a senior assistant in the Machine Learning and Computational Biology Lab of Prof. Dr. Karsten Borgwardt at ETH Zurich. His main research interests are algorithms for graph classification and time series analysis, with a focus on personalized medicine. Bastian is also enticed by finding new ways to explain neural networks using concepts from algebraic and differential topology. He is a big proponent of scientific outreach and enjoys blogging about his research, academia, supervision, and software development. Bastian received his M.Sc. Degree in mathematics, as well as his Ph.D. in computer science, from Heidelberg.
Contact Ginny Watterson for Zoom link.