“A connubio of Machine Learning and PDEs for Scientific Discovery in the Biological Sciences”  by Alessandro Selvitella, PhD, Assistant Professor in Mathematics Sciences,  Purdue University. 

In this talk, I will concentrate on problems that necessitate scientific domain knowledge and a combination of tools from differential equations and machine learning to be solved. In particular, I will outline some results on problems emerging in biomechanics, neuroscience, and infectious disease dynamics that benefit from different combinations of methods, such as optimization, asymptotic analysis, stability theory, and transfer learning.

Bio: Alessandro Maria Selvitella received a BSc and an MSc in Mathematics from Universita’ degli Studi di Milano (Milan, Italy), 
a PhD in Mathematical Analysis from SISSA (Trieste, Italy), an MSc and a PhD in Statistics from McMaster University (Hamilton, Canada). Alessandro has been a Postdoctoral Fellow in Applied Mathematics at McMaster University and he has been a Postdoctoral Fellow in the Departments of Psychiatry and Computing Science at the University of Alberta. Alessandro is currently an Assistant Professor in the Department of Mathematical Sciences at Purdue University Fort Wayne. Alessandro’s current research interests are in 
the theory and applications of Machine Learning methods to the Biological and Medical Sciences. Alessandro received, among 
the others, two Faculty Enhanced Research Appointments from Purdue (first ever at PFW in 2024) and a Seed for Success Award in 2024. He is an Editorial Board member of Nature Scientific Reports and Chief Scientist and Founder of the Laboratory of 
Data Science at Purdue University Fort Wayne.