“Combined Discriminative-Generative AI Techniques for Robust Scene Perception in Adversarial Environments”
Despite the strengths of deep learning using convolutional neural networks (CNNs), they have several vulnerabilities, such as their opacity in understanding how its decisions are made, fragility for generalizing beyond overfit training examples, and inflexibility for recovering when false decisions are produced. The weaknesses of CNNs play to the strengths of robustness for generative probabilistic inference techniques (such as Monte Carlo sampling), which are inherently explainable, general, and resilient through the process of generating, evaluating, and maintaining a distribution of many hypotheses representing possible decisions. Discriminative-generative algorithms offer a promising avenue for robust perception. Such methods combine inference by deep learning with sampling and probabilistic inference models to achieve robust and adaptive perception, which allows intelligent systems to reason about, interact with, and manipulate objects under input variation and even adversarial conditions. In this talk, I will present our latest work on Generative Robust Inference and Perception (GRIP) and describe how it may be used to improve robot performance especially in unstructured and cluttered environments. I will also discuss our ongoing plans to accelerate these algorithms in hardware.
R. Iris Bahar received the B.S. and M.S. degrees in computer engineering from the University of Illinois, Urbana-Champaign, and the Ph.D. degree in electrical and computer engineering from the University of Colorado, Boulder. Before entering the Ph.D program at CU-Boulder, she worked for Digital Equipment Corporation on their VAX microprocessor designs. She has been on the faculty at Brown University since 1996 and now holds a dual appointment as Professor of Engineering and Professor of Computer Science. Her teaching covers topics such as digital logic, computer architecture, and robot design. Her research interest have centered on energy-efficient and reliable computing, from the system level to device level. Most recently, this includes the design of robotic systems. She served as the Program Chair and General Chair of the International Conference on Computer-Aided Design (ICCAD) in 2017, 2018 respectively and the General Chair of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) in 2019. She is the 2019 recipient of the Marie R. Pistilli Women in Electronic Design Award and the Brown University School of Engineering Award for Excellence in Teaching in Engineering.