Seminars & Colloquia
University of California - Santa Barbara
"Elastic Processing and Hardware Architectures for Machine Learning"
Thursday January 27, 2022 02:00 PM
Location: 3211, EB2 NCSU Centennial Campus
Zoom Meeting Info (Visitor parking instructions)
My approach to the performance and energy-efficiency challenges can be encapsulated in a few questions. Do we need all the computations and data movements involved in conventional ML processing? Does redundancy exist at the hardware level? How can we better approach large-scale ML problems with new computing paradigms? What are the implications for architectures with more focus on privacy, robustness, and security? In this talk, I will present how to explore the elasticity in ML processing and hardware architectures: from the algorithm perspective, I propose redundancy-aware processing in DNN training and inference, as well as large-scale classification problems and long-range Transformers; from the architecture perspective, I explore balanced, specialized, and flexible designs to improve efficiency.
Host: Frank Mueller, CSC