search menu icon-carat-right cmu-wordmark

Juneberry - Tutorial

March 2022 Presentation
Andrew O. Mellinger, Nathan M. VanHoudnos, Nick Winski

Presented at Naval Applications of Machine Learning 2022, this tutorial reviews Juneberry, a reproducible research framework to build, maintain, and evaluate ML with declarative configs.

Publisher:

Software Engineering Institute

Abstract

Researchers at the SEI’s AI Division have developed Juneberry, a tool to improve the automation, evaluation, and comparison of multiple ML models to make these predictions as accurate as possible. It automates loading and preparing training data, constructing and executing models, generating inferences from test datasets, producing reports, and organizing and managing different types of output. Juneberry is open-source and can be cloned or downloaded via Github.

This tutorial walks users through steps for reproducing the results of a paper and was presented Andrew Mellinger, Nick Winski, and Nathan VanHoudnos at Naval Applications of Machine Learning 2022 on March 22, 2022.