•   When: Friday, December 02, 2022 from 11:00 AM to 12:00 PM
•   Speakers: Aidong Zhang Departments of Computer Science, University of Virginia
•   Location: Research Hall 163
•   Export to iCal

Abstract: The past decade has been a very exciting time for machine learning (ML) research. Significant research effort has focused on improving predictive performance of Deep Neural Networks (DNN) by proposing increasingly complex architectures which have surpassed even human-level performance. Even though these methods demonstrate incredible potential in saving valuable man-hours and minimizing inadvertent human mistakes, their adoption has been met with rightful skepticism and extreme circumspection in critical applications like medical diagnosis, credit risk analysis, etc. The most paramount of these challenges is the lack of rationale behind DNN predictions - making them notoriously black-box in nature. In extreme cases, this can create a lack of alignment between the designer's intended behavior and the model's actual performance. Recently, there have been multiple concept-based model architectures proposed which incorporate concepts during model training. It is believed that explaining model predictions using abstract human-understandable ``concepts'' better aligns model's internal working with human thought process. In this talk, I will discuss some of the latest techniques on robustness and interpretability of ML approaches. I will discuss the concept learning models and how generalizable concepts can be learned. I will also discuss the robustness of the concepts-based models to adversarial perturbations.

Short Bio: Dr. Aidong Zhang is a William Wulf Faculty Fellow and Professor of Computer Science in the School of Engineering and Applied Sciences at University of Virginia (UVA). She also holds joint appointments with Department of Biomedical Engineering and School of Data Science at University of Virginia. Her research interests include machine learning, data mining, bioinformatics, and health informatics. Dr. Zhang is a fellow of ACM, AIMBE, and IEEE.