Poster Open Access

Interpretability for computational biology

Nguyen An-phi; Rodriguez-Martinez


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.3374361", 
  "title": "Interpretability for computational biology", 
  "issued": {
    "date-parts": [
      [
        2019, 
        8, 
        22
      ]
    ]
  }, 
  "abstract": "<p>Why do we need interpretability to unveil the decision process ofa machine learning model?<br>\nTrust - for high-risk scenarios, e.g. healthcare, the user needs to trust the decision taken.<br>\nDebugging -&nbsp;the model may be badly trained or there might be an unfair bias in either the dataset or the model itself.<br>\nHypothesis generation - surprising results might be consequences of new mechanisms or patterns unknown even to field experts.</p>", 
  "author": [
    {
      "family": "Nguyen An-phi"
    }, 
    {
      "family": "Rodriguez-Martinez"
    }
  ], 
  "id": "3374361", 
  "event-place": "Basel, Switzerland", 
  "type": "graphic", 
  "event": "27th Conference on Intelligent Systems for Molecular Biology and the 18th European Conference on Computational Biology (ISMB/ECCB 2019)"
}
175
185
views
downloads
All versions This version
Views 175175
Downloads 185185
Data volume 48.9 MB48.9 MB
Unique views 162162
Unique downloads 179179

Share

Cite as