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

2020/12/29 by Weiss, Michael, Tonella, Paolo
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Software Engineering (cs.SE)

paper · doi:10.48550/arxiv.2101.00982

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.

Related

• Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantification
• A Survey of Uncertainty in Deep Neural Networks
• Uncertainty Quantification for Deep Learning
• A Survey on Uncertainty Quantification Methods for Deep Learning
• Uncertainty quantification for trustworthy deep learning: Methods and measures