Sign Up
Log in Sign up

IMSE Seminar: "Energy-Efficient Neuro-Symbolic AI Hardware with CMOS+X"

Monday, March 31, 2025 1 PM to 1:50 PM

I'm Interested
Dr. Haitong Li, Purdue University
I'm Interested

About this Event

Stephen F. & Camilla T. Brauer Hall, 12 View map

6548 Forest Park Pkwy, St. Louis, MO 63112, USA

View map

Dr. Haitong Li, Assistant Professor, Elmore Family School of Electrical and Computer Engineering, Purdue University 

Neuro-symbolic computing merges human-like symbolic learning and reasoning with hierarchical, context-based neural representations, marking a new frontier of edge AI due to the enhanced learning capability, robustness, and explainability. With neuro-symbolic models handling data-intensive workloads, energy-efficient hardware fabrics and flexible architecture integration are needed for sustained efficiency bridging the edge-cloud continuum. In this talk, I will discuss how we could meet such application demands by exploiting the 3D integration of emerging device technologies with silicon CMOS ("CMOS+X"), while exploring vast design space exposed from material/device level to architecture level with several case studies.

Event Details

Event Type

Lectures & Presentations

Schools

Arts & Sciences McKelvey School of Engineering

Topic

Science & Technology

Department

Institute of Materials Science & Engineering

Event Contact

Beth Gartin, bgartin@wustl.edu

Speaker Information

Haitong Li is an Assistant Professor in the Elmore Family School of Electrical and Computer Engineering at Purdue University. He obtained his Ph.D. and M.S. in Electrical Engineering from Stanford University advised by Prof. H.-S. Philip Wong, and B.S. from Peking University. He was a visiting researcher with Silicon Research Group at Meta Reality Labs. His research interests are in the new memory device technologies, circuit designs, and 3D integration for energy-efficient computing towards ubiquitous machine intelligence. He has published over 60 papers broadly across the technology stack (IEDM, VLSI, ISSCC, JSSC, Nature Electronics, DAC, DATE, ISCA) with over 3500 citations. His work was featured as part of the “New Compute Trajectories for Energy-Efficient Computing” in SRC’s pivotal roadmap, “The Decadal Plan for Semiconductors”.

See Who Is Interested

0 people are interested in this event

I'm Interested