Building an Edge Machine Learning System

October 1st, 2020

The standard way of training and deploying Machine Learning (ML) models is with centralized architectures. This means that there are centralized servers, that receive requests from devices and respond with ML predictions. These systems have the disadvantange, as with any other centralized system, that they can be overloaded and that they must have central access to all data. In this course we show how distributed ML systems can be trained and deployed in a way that eliminates some of the problems of centralized architectures.


Coming soon: online store

Subscribe to newsletter to be notified.

Comment to help prioritize content.

Learn more: "A User-Driven Knowledge Center"



AUTHOR
I help companies through digital transformations by designing and developing systems that improve human decision making with data, cloud, software, and mathematics (Machine Learning, Operations Research, Statistics). I also enjoy coaching teams and publishing content on Smart Automation.

Comments

Comments not loaded in development.

Recommended