Active Evaluation Software for Selection of Ground Truth Labels

Description

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.

Resources

Name Format Description Link
0 https://doi.org/10.18434/M32227

Tags

  • ar
  • active-evaluation
  • machine-learning

Topics

Categories