You are here

FAU Collections » FAU Research Repository » FAU Theses and Dissertations

OPTIMIZED DEEP LEARNING ARCHITECTURES AND TECHNIQUES FOR EDGE AI

Download pdf | Full Screen View

Date Issued:
2021
Abstract/Description:
The recent rise of artificial intelligence (AI) using deep learning networks allowed the development of automatic solutions for many tasks that, in the past, were seen as impossible to be performed by a machine. However, deep learning models are getting larger, need significant processing power to train, and powerful machines to use it. As deep learning applications become ubiquitous, another trend is taking place: the growing use of edge devices. This dissertation addresses selected technical issues associated with edge AI, proposes novel solutions to them, and demonstrates the effectiveness of the proposed approaches. The technical contributions of this dissertation include: (i) architectural optimizations to deep neural networks, particularly the use of patterned stride in convolutional neural networks used for image classification; (ii) use of weight quantization to reduce model size without hurting its accuracy; (iii) systematic evaluation of the impact of image imperfections on skin lesion classifiers' performance in the context of teledermatology; and (iv) a new approach for code prediction using natural language processing techniques, targeted at edge devices.
Title: OPTIMIZED DEEP LEARNING ARCHITECTURES AND TECHNIQUES FOR EDGE AI.
67 views
27 downloads
Name(s): Zaniolo, Luiz, author
Marques, Oge, Thesis advisor
Florida Atlantic University, Degree grantor
Department of Computer and Electrical Engineering and Computer Science
College of Engineering and Computer Science
Type of Resource: text
Genre: Electronic Thesis Or Dissertation
Date Created: 2021
Date Issued: 2021
Publisher: Florida Atlantic University
Place of Publication: Boca Raton, Fla.
Physical Form: application/pdf
Extent: 129 p.
Language(s): English
Abstract/Description: The recent rise of artificial intelligence (AI) using deep learning networks allowed the development of automatic solutions for many tasks that, in the past, were seen as impossible to be performed by a machine. However, deep learning models are getting larger, need significant processing power to train, and powerful machines to use it. As deep learning applications become ubiquitous, another trend is taking place: the growing use of edge devices. This dissertation addresses selected technical issues associated with edge AI, proposes novel solutions to them, and demonstrates the effectiveness of the proposed approaches. The technical contributions of this dissertation include: (i) architectural optimizations to deep neural networks, particularly the use of patterned stride in convolutional neural networks used for image classification; (ii) use of weight quantization to reduce model size without hurting its accuracy; (iii) systematic evaluation of the impact of image imperfections on skin lesion classifiers' performance in the context of teledermatology; and (iv) a new approach for code prediction using natural language processing techniques, targeted at edge devices.
Identifier: FA00013822 (IID)
Degree granted: Dissertation (Ph.D.)--Florida Atlantic University, 2021.
Collection: FAU Electronic Theses and Dissertations Collection
Note(s): Includes bibliography.
Subject(s): Artificial intelligence
Deep learning (Machine learning)
Neural networks (Computer science)
Persistent Link to This Record: http://purl.flvc.org/fau/fd/FA00013822
Use and Reproduction: Copyright © is held by the author with permission granted to Florida Atlantic University to digitize, archive and distribute this item for non-profit research and educational purposes. Any reuse of this item in excess of fair use or other copyright exemptions requires permission of the copyright holder.
Use and Reproduction: http://rightsstatements.org/vocab/InC/1.0/
Host Institution: FAU
Is Part of Series: Florida Atlantic University Digital Library Collections.