Date of Award

5-2020

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Engineering and Sciences

First Advisor

Carlos Otero

Second Advisor

Veton Kepuska

Third Advisor

William Allen

Fourth Advisor

Philip Bernhard

Abstract

Edge devices are undergoing groundbreaking computing transformation, which lets us tap into artificial intelligence, quantum computing, 5th generation network capability, fog networking, and computing complex algorithms. Edge systems have substantial advantages over the conventional system in terms of scalability, optimized resources, reliability, and security. The proliferation of such resource-constrained devices in recent years has resulted in the generation of a large quantity of data; these data-producing devices are attractive targets for applications of machine learning. Machine learning models, especially deep learning neural networks, produced models that have high accuracy and prediction capability, but it comes at the cost of computation power and memory consumption. There is a large scope to optimize machine learning models over certain criteria such as size, efficiency, latency, and accuracy. Optimization of machine learning models and running them over a constrained environment will help revolutionize edge devices and help develop exceptional results in real-time.

Download

Share

COinS