Energy-Efficient DNN Training Processors on Micro-AI Systems

Energy-Efficient DNN Training Processors on Micro-AI Systems

Many edge/mobile devices are now able to utilize deep neural networks (DNNs) thanks to the development of mobile DNN accelerators. Mobile DNN accelerators overcame the problems of limited computing resources and battery capacity by realizing energy-efficient inference. However, its passive behavior...

Full description

Bibliographic Details
Main Authors: Donghyeon Han, Sanghoon Kang, Sangyeob Kim, Juhyoung Lee, Hoi-Jun Yoo
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Open Journal of the Solid-State Circuits Society
Subjects:
Backpropagation (BP)
backward unlocking (BU)
bit-precision optimization
deep neural network (DNN) training
reading transposed weight
sparsity exploitation
Online Access:https://ieeexplore.ieee.org/document/9935273/

Internet

https://ieeexplore.ieee.org/document/9935273/

Similar Items