Prof. Iris Bahar at the Wilson Lecture Series
Scalable ML Architectures for Real-time Energy-efficient Computing
Despite the strengths of convolutional neural networks (CNNs) for object recognition, these discriminative techniques have several shortcomings that leave them vulnerable to exploitation from adversaries. Discriminative-generative approaches offers a promising avenue for robust perception by combining inference by deep learning with sampling and probabilistic inference models to achieve robust and adaptive understanding. Our focus is on implementing a scalable, computationally efficient generative inference stage that can achieve real-time results in an energy efficient manner. In this talk, I will present our work on a discriminative-generative approach for pose estimation that offers high accuracy especially in unstructured and adversarial environments. I will then describe our hardware implementation of this algorithm to obtain real-time performance with high energy-efficiency and its implications for future directions in designing scalable and efficient ML algorithms.
About the speaker
R. Iris Bahar received the B.S. and M.S. degrees in computer engineering from the University of Illinois, Urbana, and the Ph.D. degree in electrical and computer engineering from the University of Colorado, Boulder. She recently joined the faculty at the Colorado School of Mines in January 2022 and serves at Department Head of Computer Science. Before joining Mines, she was on the faculty at Brown University since 1996 and held dual appointments as Professor of Engineering and Professor of Computer Science. Her research interests focus on energy-efficient and reliable computing, from the system level to device level. Most recently, this includes the design of robotic systems. She is the 2019 recipient of the Marie R. Pistilli Women in Engineering Achievement Award and the Brown University School of Engineering Award for Excellence in Teaching in Engineering. She is a fellow of the IEEE and a ACM Distinguished Scientist.