Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Adapting Multigrid-in-Time to Train Deep Neural Networks [Slides]

Conference ·
DOI:https://doi.org/10.2172/2004439· OSTI ID:2004439
 [1];  [2];  [3];  [4];  [5];  [6];  [1];  [7];  [8]
  1. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
  2. Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
  3. Emory Univ., Atlanta, GA (United States)
  4. Univ. of New Mexico, Albuquerque, NM (United States)
  5. Technical Univ. of Kaiserslautern (Germany)
  6. Korea Aerospace University (KAU), Goyang (South Korea)
  7. Mathworks, Natick, MA (United States)
  8. Rice Univ., Houston, TX (United States)
+ Show Author Affiliations

Abstract not provided.

Research Organization:
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR); USDOE National Nuclear Security Administration (NNSA)
DOE Contract Number:
NA0003525
OSTI ID:
2004439
Report Number(s):
SAND2022--11168C; 709293
Country of Publication:
United States
Language:
English

Similar Records

Robust architectures initialization and training for deep neural networks via the adaptive basis interpretation.
Conference · Thu Apr 01 00:00:00 EDT 2021 · OSTI ID:1866561
Robust architectures, initialization, and training for deep neural networks via the adaptive basis interpretation.
Conference · Wed Sep 01 00:00:00 EDT 2021 · OSTI ID:1889595
Parallel-In-Time Training of Recurrent Neural Networks.
Conference · Fri Apr 01 00:00:00 EDT 2022 · OSTI ID:2002170

Related Subjects

97 MATHEMATICS AND COMPUTING