EDAML 2022 Invited Speaker 3: Scalable ML Architectures for Real-time Energy-efficient Computing

Abstract

Technological advancements have led to a proliferation machine learning systems to assist humans in a wide range of tasks. However, we are still far from accurate, reliable, and resource-efficient operations for many of these systems. 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. In addition, the computational cost incurred to train these discriminative models can be quite significant. Discriminative-generative approaches offers a promising avenue for robust perception and action. Such methods combine inference by deep learning with sampling and probabilistic inference models to achieve robust and adaptive understanding. In this talk, I will present our work on implementing a scalable, computationally efficient generative inference algorithm in hardware that can achieve real-time results in an energy efficient manner. I will also discuss future directions in designing scalable and efficient ML algorithms in hardware more broadly.