Adaptive Precision Training for Resource Constrained Devices

by   Tian Huang, et al.

Learn in-situ is a growing trend for Edge AI. Training deep neural network (DNN) on edge devices is challenging because both energy and memory are constrained. Low precision training helps to reduce the energy cost of a single training iteration, but that does not necessarily translate to energy savings for the whole training process, because low precision could slows down the convergence rate. One evidence is that most works for low precision training keep an fp32 copy of the model during training, which in turn imposes memory requirements on edge devices. In this work we propose Adaptive Precision Training. It is able to save both total training energy cost and memory usage at the same time. We use model of the same precision for both forward and backward pass in order to reduce memory usage for training. Through evaluating the progress of training, APT allocates layer-wise precision dynamically so that the model learns quicker for longer time. APT provides an application specific hyper-parameter for users to play trade-off between training energy cost, memory usage and accuracy. Experiment shows that APT achieves more than 50 more savings of training energy and memory usage can be achieved in return for a 1


page 1

page 2

page 3

page 4


RCT: Resource Constrained Training for Edge AI

Neural networks training on edge terminals is essential for edge AI comp...

On-FPGA Training with Ultra Memory Reduction: A Low-Precision Tensor Method

Various hardware accelerators have been developed for energy-efficient a...

Layer-Wise Partitioning and Merging for Efficient and Scalable Deep Learning

Deep Neural Network (DNN) models are usually trained sequentially from o...

Dual Precision Deep Neural Network

On-line Precision scalability of the deep neural networks(DNNs) is a cri...

TinyTrain: Deep Neural Network Training at the Extreme Edge

On-device training is essential for user personalisation and privacy. Wi...

Low-Memory Neural Network Training: A Technical Report

Memory is increasingly often the bottleneck when training neural network...

How Low Can We Go: Trading Memory for Error in Low-Precision Training

Low-precision arithmetic trains deep learning models using less energy, ...

Please sign up or login with your details

Forgot password? Click here to reset