University of Waterloo

Machine Learning Theory-Guided Solutions

Prof. Sirisha Rambhatla, Management Sciences

Nov 26, 2022, 11:30am EC4-2101A

Learning and leveraging patterns from data has fueled the recent major advances in data driven services. As these solutions become ubiquitous and get incorporated into critical applications such as healthcare and transportation, there is an increasing need to understand their decision-making mechanism to know their limits and develop new algorithms with guarantees. My research aims to develop reliable and theory-guided machine learning (ML) solutions for these critical real-world applications.

In this talk, I will present an overview of my research efforts which focus on: a) building ML algorithms with performance guarantees, b) developing model-agnostic interpretability techniques to understand deep learning model decisions , and c) enabling learning from limited data by leveraging physics-based domain knowledge, with applications to d) artificial intelligence (AI) for surgery and healthcare, e) target localization in hyperspectral images, and f) weather and air quality forecasting. Additionally, I will discuss some exciting upcoming projects and research directions to spark collaborations with the Video and Image Processing (VIP) lab.