Report Open Access

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

Michael Weiss; Paolo Tonella

JSON-LD ( Export

  "description": "<p>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.&nbsp;We present Uncertainty-Wizard, a tool that allows to quantify such uncertainty and confidence in&nbsp; artificial neural networks.&nbsp;It is built on top of the industry-leading tf.keras deep learning API and it provides a near-transparent and&nbsp; easy to understand interface.&nbsp;At the same time, it includes major performance optimizations that we benchmarked on two different machines and different configurations.</p>", 
  "license": "", 
  "creator": [
      "affiliation": "Universit\u00e0 della Svizzera italiana", 
      "@type": "Person", 
      "name": "Michael Weiss"
      "affiliation": "Universit\u00e0 della Svizzera italiana", 
      "@type": "Person", 
      "name": "Paolo Tonella"
  "headline": "Uncertainty-Wizard: Fast and User-Friendly Neural Network Uncertainty Quantification", 
  "image": "", 
  "datePublished": "2021-06-01", 
  "url": "", 
  "@context": "", 
  "identifier": "", 
  "@id": "", 
  "@type": "ScholarlyArticle", 
  "name": "Uncertainty-Wizard: Fast and User-Friendly Neural Network Uncertainty Quantification"
All versions This version
Views 4747
Downloads 3232
Data volume 21.1 MB21.1 MB
Unique views 4141
Unique downloads 3030


Cite as