In our previous video, you were introduced to AZIMUTH, an open-source software project from ServiceNow. Azimuth is an application that helps AI practitioners better understand their dataset and model predictions by performing thorough dataset and error analyses. The application leverages different tools, including robustness tests, semantic similarity analysis, and saliency maps, unified by concepts such as smart tags and proposed actions.

In this video, we will show you how to get started.

1) Simply install the latest release of Azimuth with Docker (https://servicenow.github.io/azimuth/getting-started/a-install/)

2) Learn the basics (https://servicenow.github.io/azimuth/getting-started/b-basics/)

3) Try out the tools on your own data (https://servicenow.github.io/azimuth/getting-started/c-run/)

If you would like to use Azimuth for your own projects, please be so kind as to use the following citation:

@software{Branchaud-Charron_Azimuth_an_open-source_2022,
author = {Branchaud-Charron, Frederic and Gauthier-Melancon, Gabrielle and Marinier, Joseph and Brin, Lindsay and Tyler, Chris and Le, Di and Grande, Karine and Babu, Nandhini},
doi = {10.5281/zenodo.6511558},
month = {5},
title = {{Azimuth, an open-source dataset and error analysis tool for text classification}},
url = {https://github.com/ServiceNow/azimuth},
version = {2.1},
year = {2022}
}