HNPU-V1: An Adaptive DNN Training Processor Utilizing Stochastic Dynamic Fixed-Point and Active Bit-Precision Searching
D Han, HJ Yoo - On-Chip Training NPU-Algorithm, Architecture and …, 2023 - Springer
This chapter presents HNPU, which is an energy-efficient DNN training processor by
adopting algorithm–hardware co-design. The HNPU supports stochastic dynamic fixed-point …
adopting algorithm–hardware co-design. The HNPU supports stochastic dynamic fixed-point …
Maximizing communication efficiency for large-scale training via 0/1 adam
1-bit gradient compression and local steps are two representative techniques that enable
drastic communication reduction in distributed SGD. Their benefits, however, remain an …
drastic communication reduction in distributed SGD. Their benefits, however, remain an …
A mobile DNN training processor with automatic bit precision search and fine-grained sparsity exploitation
In this article, an energy-efficient deep learning processor is proposed for deep neural
network (DNN) training in mobile platforms. Conventional mobile DNN training processors …
network (DNN) training in mobile platforms. Conventional mobile DNN training processors …
[图书][B] On-Chip Training NPU-Algorithm, Architecture and SoC Design
D Han, HJ Yoo - 2023 - Springer
Deep learning becomes the mainstream of artificial intelligence applications and its demand
is increasing day by day. Previously, deep learning was only considered for cloud-server …
is increasing day by day. Previously, deep learning was only considered for cloud-server …
PWPROP: A Progressive Weighted Adaptive Method for Training Deep Neural Networks
In recent years, adaptive optimization methods for deep learning have attracted
considerable attention. AMSGRAD indicates that the adaptive methods may be hard to …
considerable attention. AMSGRAD indicates that the adaptive methods may be hard to …
An Energy-Efficient Deep Neural Network Training Processor with Bit-Slice-Level Reconfigurability and Sparsity Exploitation
This paper presents an energy-efficient deep neural network (DNN) training processor
through the four key features: 1) Layer-wise Adaptive bit-Precision Scaling (LAPS) with 2) In …
through the four key features: 1) Layer-wise Adaptive bit-Precision Scaling (LAPS) with 2) In …
Introduction to Semi-discrete Calculus
A Shachar - arXiv preprint arXiv:1012.5751, 2010 - arxiv.org
The Infinitesimal Calculus explores mainly two measurements: the instantaneous rates of
change and the accumulation of quantities. This work shows that scientists, engineers …
change and the accumulation of quantities. This work shows that scientists, engineers …