Breakthroughs in AI and ML have spurred a gold-rush in exploring novel solutions in a wide range of industrial applications. Recent innovations boldly aim to apply deep learning to safety- and business-critical systems. Self-driving cars, learning-enabled hospital and medical systems, smart manufacturing systems, and AI-supported mining industry require rigorous safety and performance guarantees. But can learning-enabled systems be trusted?

In this webinar, Dr. Trivedi shows that deep learning systems lack robustness and correctness guarantees. Then he will showcase how research in verification and validation techniques can build trust in the next generation of learning-enabled systems.

Ashutosh Trivedi is an assistant professor of computer science at the University of Colorado Boulder. His research interests lie at the intersection of computer science, control theory, and machine learning. His research focuses on developing and applying rigorous mathematical reasoning techniques for the design and analysis of learning-enabled cyber-physical systems. He received his doctorate in computer science with a focus on game theory and optimization from the University of Warwick. Prior to joining the University of Colorado Boulder, Ashutosh worked as an assistant professor of computer science at the Indian Institute of Technology Bombay. He has spent time as a research fellow at a number of institutions such as University of Pennsylvania and the University of Oxford.

About the Series

The monthly PPI Advances Series is targeted towards industrial practitioners to (i) give an overview of an area and its industrial applications from one of our faculty experts and (ii) allow industry participants to engage with the presenter to shape the research to be of the most value to industry. We are looking forward to serving you, and please invite your colleagues to attend these webinars.