Publication Date

2021

School

School of Engineering and Computational Sciences

Major

Engineering: Computer

Keywords

Deep Learning, Internet of Things, voice recognition, image recognition

Disciplines

Artificial Intelligence and Robotics | OS and Networks | Systems Architecture

Abstract

The Internet of Things (IoT) is utilizing Deep Learning (DL) for applications such as voice or image recognition. Processing data for DL directly on IoT edge devices reduces latency and increases privacy. To overcome the resource constraints of IoT edge devices, the computation for DL inference is distributed between a cluster of several devices. This paper explores DL, IoT networks, and a novel framework for distributed processing of DL in IoT clusters. The aim is to facilitate and simplify deployment, testing, and study of a distributed DL system, even without physical devices. The contributions of this paper are a deployment of the framework to an Ubuntu virtual machine testbed and a repackaging of the framework as a Docker image for portability and fast future deployment.

Download

Share

COinS