English

Uncertainty-Wizard: Fast and User-Friendly Neural Network Uncertainty Quantification

Machine Learning 2021-01-29 v2 Software Engineering

Abstract

Uncertainty and confidence have been shown to be useful metrics in a wide variety of techniques proposed for deep learning testing, including test data selection and system supervision.We present uncertainty-wizard, a tool that allows to quantify such uncertainty and confidence in artificial neural networks. It is built on top of the industry-leading tf.keras deep learning API and it provides a near-transparent and easy to understand interface. At the same time, it includes major performance optimizations that we benchmarked on two different machines and different configurations.

Keywords

Cite

@article{arxiv.2101.00982,
  title  = {Uncertainty-Wizard: Fast and User-Friendly Neural Network Uncertainty Quantification},
  author = {Michael Weiss and Paolo Tonella},
  journal= {arXiv preprint arXiv:2101.00982},
  year   = {2021}
}

Comments

Accepted for publication at the IEEE International Conference on Software Testing, Verification and Validation 2021

R2 v1 2026-06-23T21:45:11.368Z