The University of Southampton
University of Southampton Institutional Repository

Improving training and inference for embedded machine learning

Improving training and inference for embedded machine learning
Improving training and inference for embedded machine learning
Many emerging applications are driving the development of Artificial Intelligence (AI) for embedded systems that require AI models to operate in resource constrained environments. Desirable characteristics of these models are reduced memory, computation and power requirements, that still deliver powerful performance. Deep learning has evolved as the state-of-the-art machine learning paradigm becoming more widespread due to its power in exploiting large datasets for inference. However, deep learning techniques are computationally and memory intensive, which may prevent them from being deployed effectively on embedded platforms with limited resources and power budgets. To address this problem, I focus on improving the efficiency of these algorithms. I show that improved compression and optimization algorithms can be applied to the deep learning framework from training through inference to meet this goal. This thesis introduces a new compression method that significantly reduces the number of parameters requirements of deep learning models by first-order optimization and sparsity-inducing regularization. This compression method can reduce model size by up to 300× without sacrificing prediction accuracy. To improve the performance of deep learning models, optimization techniques become more important, especially in large-scale applications. As a result, I develop two new first-order optimization algorithms that improve over existing methods by controlling the variance of the gradients, determining optimal batch sizes, scheduling adaptive learning rates, and balancing biased/unbiased estimations of the gradients, which can improve the convergence rate to provide a lower computational complexity
University of Southampton
Bi, Jia
8b23da1b-a6d6-43f4-9752-04a825093b3b
Bi, Jia
8b23da1b-a6d6-43f4-9752-04a825093b3b
Gunn, Stephen
306af9b3-a7fa-4381-baf9-5d6a6ec89868

Bi, Jia (2020) Improving training and inference for embedded machine learning. Doctoral Thesis, 130pp.

Record type: Thesis (Doctoral)

Abstract

Many emerging applications are driving the development of Artificial Intelligence (AI) for embedded systems that require AI models to operate in resource constrained environments. Desirable characteristics of these models are reduced memory, computation and power requirements, that still deliver powerful performance. Deep learning has evolved as the state-of-the-art machine learning paradigm becoming more widespread due to its power in exploiting large datasets for inference. However, deep learning techniques are computationally and memory intensive, which may prevent them from being deployed effectively on embedded platforms with limited resources and power budgets. To address this problem, I focus on improving the efficiency of these algorithms. I show that improved compression and optimization algorithms can be applied to the deep learning framework from training through inference to meet this goal. This thesis introduces a new compression method that significantly reduces the number of parameters requirements of deep learning models by first-order optimization and sparsity-inducing regularization. This compression method can reduce model size by up to 300× without sacrificing prediction accuracy. To improve the performance of deep learning models, optimization techniques become more important, especially in large-scale applications. As a result, I develop two new first-order optimization algorithms that improve over existing methods by controlling the variance of the gradients, determining optimal batch sizes, scheduling adaptive learning rates, and balancing biased/unbiased estimations of the gradients, which can improve the convergence rate to provide a lower computational complexity

Text
Jia Bi_ Phd_ Cyber Physical Systems research group_ 09_10_2020 (1)
Available under License University of Southampton Thesis Licence.
Download (1MB)
Text
PTDThesis_BI-SIGNED
Restricted to Repository staff only

More information

Published date: September 2020

Identifiers

Local EPrints ID: 447797
URI: http://eprints.soton.ac.uk/id/eprint/447797
PURE UUID: ec2feeb2-1563-449d-aea9-9c1e28d1ba07

Catalogue record

Date deposited: 23 Mar 2021 17:30
Last modified: 23 Mar 2021 17:35

Export record

Contributors

Author: Jia Bi
Thesis advisor: Stephen Gunn

University divisions

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×