Description: In this talk, we discuss both the hardware and software methodologies for fast inferencing at the edge. Specifically, we discuss modern AI accelerators and why they are fast and energy efficient. This typically involves performing computational transforms, reduced precision via quantization, and network pruning. We also discuss various neural network architectures in terms of their size and efficiency.
Presenter(s): Dr. Wes Brewer - PET GDIT
Location: Webcast
Date & Time: February 18, 2020, 3:00p - 4:30p ET
Additional Notes: Part of the HPDA Seminar Series (2020).
Distribution Statement C. Distribution a authorized to U.S. Government Agencies and their contractors, Administrative or Operational Use, 18 February 2020. Other requests for this document shall be referred to the High Performance Computing Modernization Office, 3909 Halls Ferry Road, Vicksburg, MS 39180.