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

TL;DR

Uncertainty-Wizard is a user-friendly tool built on tf.keras that efficiently quantifies neural network uncertainty and confidence, aiding in deep learning testing and system supervision.

Contribution

It introduces a fast, accessible uncertainty quantification tool integrated with tf.keras, with performance optimizations and benchmarking across different setups.

Findings

Achieves fast uncertainty estimation in neural networks.

Provides a transparent interface for users.

Demonstrates performance improvements through benchmarking.

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.