Date: Friday, September 27, 2019
Time: 12:00 PM – 1:00 PM (EDT)
Speaker: Kushal Datta, Intel Corporation
Location: Borg Warner Auditorium, Institute for Advanced Vehicle Systems Building (IAVS), Dearborn, MI 48128
Cost: none
RSVP: required
Event Details & Registration:Â https://umdearborn.edu/events/all-events/industrial-speaker-series-kushal-datta
Deep Neural Networks in Action – An Industry Perspective on Emergence, Adoption and Evolution of DNNs
Kushal Datta is a Senior Research Scientist in the Artificial Intelligence Products Group at Intel Corporation. He specializes in accelerating deep learning training and inference on Intel Architecture. His noteworthy achievements include optimization of Multiscale CNN training time on Multi-Node Xeon® and INT8/VNNI quantization of the Transformer model. In his previous roles, he worked on Intel® Graph Analytics Toolkit, Genomics Analytics Toolkit-4.0 (from Broad Institute) and TileDB (a multi-dimensional array store). Dr. Datta received his PhD in ECE from University of North Carolina at Charlotte where he created a famous cycle-accurate micro-architecture simulator called Casper. His doctoral work used statistical machine learning and Casper to improve power efficiency of simultaneous multi-threading SPARCV9 very large-core microarchitectures.