An Adaptive Basis Perspective to Improve Initialization and Accelerate Training of DNNs.
Abstract not provided.
- Research Organization:
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
- DOE Contract Number:
- NA0003525
- OSTI ID:
- 1847582
- Report Number(s):
- SAND2021-2260C; 694184
- Resource Relation:
- Conference: Proposed for presentation at the SIAM Conference on Computational Science and Engineering (CSE21).
- Country of Publication:
- United States
- Language:
- English
Similar Records
An Adaptive Basis Perspective to Improve Initialization and Accelerate Training of DNNs.
Robust architectures initialization and training for deep neural networks via the adaptive basis interpretation.
Robust architectures, initialization, and training for deep neural networks via the adaptive basis interpretation.
Conference
·
2021
·
OSTI ID:1847582
+3 more
Robust architectures initialization and training for deep neural networks via the adaptive basis interpretation.
Conference
·
2021
·
OSTI ID:1847582
Robust architectures, initialization, and training for deep neural networks via the adaptive basis interpretation.
Conference
·
2021
·
OSTI ID:1847582