How to deploy your AI model on Edge devices with Azure

René Bremer
Towards Data Science
8 min readJul 14, 2019

--

1. Introduction

Edge Computing is a pattern in which part of the computation is done on decentralized edge devices and is a great way to extend cloud computing. Using this pattern, Artificial Intelligence (AI) models are trained in the cloud and deployed on the edge which has the following advantages:

  • Speed when realtime decision making is needed and cloud compute would imply too much latency
  • Availability allowing the device to function offline in case of limited connectivity…

--

--

Data Solution Architect @ Microsoft, working with Azure services as ADFv2, ADLSgen2, Azure DevOps, Databricks, Function Apps and SQL. Opinions here are mine.