Report Open Access

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

Michael Weiss; Paolo Tonella


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.5055751", 
  "author": [
    {
      "family": "Michael Weiss"
    }, 
    {
      "family": "Paolo Tonella"
    }
  ], 
  "issued": {
    "date-parts": [
      [
        2021, 
        6, 
        1
      ]
    ]
  }, 
  "abstract": "<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>", 
  "title": "Uncertainty-Wizard: Fast and User-Friendly Neural Network Uncertainty Quantification", 
  "type": "article", 
  "id": "5055751"
}
47
32
views
downloads
All versions This version
Views 4747
Downloads 3232
Data volume 21.1 MB21.1 MB
Unique views 4141
Unique downloads 3030

Share

Cite as