Active Evaluation Software for Selection of Ground Truth Labels

Published by National Institute of Standards and Technology | National Institute of Standards and Technology | Metadata Last Checked: June 27, 2025 | Last Modified: 2020-04-28 00:00:00

This software repository contains a python package Aegis (Active Evaluator Germane Interactive Selector) package that allows us to evaluate machine learning systems's performance (according to a metric such as accuracy) by adaptively sampling trials to label from an unlabeled test set to minimize the number of labels needed. This includes sample (public) data as well as a simulation script that tests different label-selecting strategies on already labelled test sets. This software is configured so that users can add their own data and system outputs to test evaluation.

Find Related Datasets

Click any tag below to search for similar datasets

active evaluation ar machine learning

Complete Metadata

bureauCode	[ "006:55" ]
identifier	ark:/88434/mds2-2227
issued	2020-07-09
landingPage	https://github.com/usnistgov/active-evaluation
language	[ "en" ]
programCode	[ "006:045" ]
theme	[ "Information Technology:Data and informatics" ]