Speaker
Philip Coleman Harris
(Massachusetts Inst. of Technology (US))
Description
A3D3 Institute, Accelerated Artificial Intelligence Algorithms for Data-Driven Discovery, aims to pursue next generation AI Algorithms combined with next generation processor technology to develop AI algorithms that can be run fast to solve real-time scientific problems with AI Domains: High Energy Physics, Multi-Messenger Astronomy, and Neuroscience. We will present Hardware-Algorithm co-design and collaborative approaches within different science domains to achieve optimal low latency and performance for science. We are also working to make Machine Learning challenges to highlight low latency domain and aiming to connect with MLPerf science and other organization with similar computational challenges.
Primary author
Philip Coleman Harris
(Massachusetts Inst. of Technology (US))
Co-authors
Mark Neubauer
(Univ. Illinois at Urbana Champaign (US))
Mark Stephen Neubauer
(Univ. Illinois at Urbana-Champaign)
Shih-Chieh Hsu
(University of Washington Seattle (US))
