Speaker "Hyeran Jeon" Details Back



Architectural Study in Deep Learning Era


Deep learning became the core algorithm of many applications recently. Deep learning enables computing devices to automatically recognize individuals in photos, cars to navigate by themselves, and medical devices to diagnose cancer. With deep learning, software developers do not need to design sophisticated algorithms to extract important features from the input data. Under this computing paradigm transition, researchers need to understand the types of applications that can be accelerated by deep learning and the performance bottlenecks of deep learning applications. In this talk, Dr. Jeon will first introduce a few example deep learning applications that her research group has developed for smart city, secure computing, and medical image processing. In the second part of the talk, she will introduce a new deep learning benchmark suite, Tango, that her research group has recently released. She will show a few in-depth architectural characterization results measured by Tango from various accelerators, which will be helpful for developing a new accelerator design.


Hyeran Jeon is an Assistant Professor at San Jose State University. Her research interests lie in energy-efficient high-throughput processor and systems design. Recently, she is leading several research projects mainly on the efficient acceleration of deep learning applications and development of new deep learning applications. Her research group is sponsored by the California Energy Commission, Lam Research, NVIDIA, and Xilinx. Before joining San Jose State University, she earned her Ph.D. at the University of Southern California in 2015 and worked for Samsung, AMD, and IBM T.J. Watson Research Center as a systems software engineer and a research intern.