Computer Science Speakers Series

Back to Listing

SPECIAL SEMINAR: Gagandeep Singh, ETH Zurich, "Certified Artificial Intelligence"

Event Type
Lecture
Sponsor
Illinois Computer Science
Location
Talk and Q&A link will be disseminated via email to limited participants
Date
Apr 3, 2020   10:00 - 11:00 am  
Cost
Free
Contact
Salome Liebenberg
E-Mail
salomel@illinois.edu
Views
386
Originating Calendar
Computer Science Speakers Calendar

Abstract: Despite remarkable success over the last decade, increasing evidence pointing to the fragility of modern data-driven AI systems has started to emerge, triggering social concerns, government regulations, and limiting wider adoption. Indeed, creating AI systems that behave safely and reliably is a fundamental challenge of critical importance. In this talk, I will present a path towards addressing this fundamental problem. Specifically, I will introduce new mathematical methods based on convex relaxations, sampling, and Lipschitz optimization that enable scalable and precise reasoning about the (potentially infinite number of) behaviors of an AI system (e.g., a deep neural network). I will then show how these methods enable both the creation of state-of-the-art automated verifiers for modern AI systems and the discovery of new provable training techniques. Finally, I will outline several promising future research directions.

 

Bio: Gagandeep Singh is a Ph.D. candidate at ETH Zurich supervised by Prof. Martin Vechev and Prof. Markus Püschel. He completed his Masters from ETH and Bachelors from the Indian Institute of Technology, Patna. His research interests lie at the intersection of automated reasoning and machine learning. He has built several systems now used in both academia and industry, including ELINA, a state-of-the-art library for fast numerical static analysis and ERAN, a state-of-the-art verifier for deep neural networks.

 

Faculty Host: Sasa Misailovic

 

 

link for robots only