skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: AWE-ML: Averaged Weights for Explainable Machine Learning v. 1.0

Abstract

This software uses averaged weighted estimators to classify instances and then explicate the individual decision process in classification. The software has state of the art performance in accuracy, while maintaining full explainability. It does this by calculating hierarchically averaged probabilities for a large class of feature combinations and updating them ‘on-the-fly’. On the fly updating also allows the model to be accurate, relative to the total dataset, maintaining accuracy in real-time, without a need to retrain the classifier.

Developers:
 [1]
  1. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Release Date:
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Programming Languages:
C++; Python
Version:
v. 1.0
Licenses:
GNU General Public License v3.0
Sponsoring Org.:
USDOE

Primary Award/Contract Number:
NA0003525
Code ID:
23770
Site Accession Number:
SCR#2308
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Country of Origin:
United States

Citation Formats

Agarwal, Sapan, and USDOE. AWE-ML: Averaged Weights for Explainable Machine Learning v. 1.0. Computer software. https://www.osti.gov//servlets/purl/1499108. Vers. v. 1.0. USDOE. 7 Mar. 2019. Web. doi:10.11578/dc.20190312.1.
Agarwal, Sapan, & USDOE. (2019, March 7). AWE-ML: Averaged Weights for Explainable Machine Learning v. 1.0 (Version v. 1.0) [Computer software]. https://www.osti.gov//servlets/purl/1499108. doi:10.11578/dc.20190312.1.
Agarwal, Sapan, and USDOE. AWE-ML: Averaged Weights for Explainable Machine Learning v. 1.0. Computer software. Version v. 1.0. March 7, 2019. https://www.osti.gov//servlets/purl/1499108. doi:10.11578/dc.20190312.1.
@misc{osti_1499108,
title = {AWE-ML: Averaged Weights for Explainable Machine Learning v. 1.0, Version v. 1.0},
author = {Agarwal, Sapan and USDOE},
abstractNote = {This software uses averaged weighted estimators to classify instances and then explicate the individual decision process in classification. The software has state of the art performance in accuracy, while maintaining full explainability. It does this by calculating hierarchically averaged probabilities for a large class of feature combinations and updating them ‘on-the-fly’. On the fly updating also allows the model to be accurate, relative to the total dataset, maintaining accuracy in real-time, without a need to retrain the classifier.},
url = {https://www.osti.gov//servlets/purl/1499108},
doi = {10.11578/dc.20190312.1},
year = {2019},
month = {3},
note =
}

Software:
Publicly Accessible Repository
https://github.com/sandialabs/aweml

Save / Share: