Doctor XAI: an ontology-based approach to black-box sequential data classification explanations

@article{Panigutti2020DoctorXA,
  title={Doctor XAI: an ontology-based approach to black-box sequential data classification explanations},
  author={Cecilia Panigutti and A. Perotti and D. Pedreschi},
  journal={Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency},
  year={2020}
}
Several recent advancements in Machine Learning involve blackbox models: algorithms that do not provide human-understandable explanations in support of their decisions. This limitation hampers the fairness, accountability and transparency of these models; the field of eXplainable Artificial Intelligence (XAI) tries to solve this problem providing human-understandable explanations for black-box models. However, healthcare datasets (and the related learning tasks) often present peculiar features… Expand
13 Citations
Teaching the Machine to Explain Itself using Domain Knowledge
  • Highly Influenced
  • PDF
A Survey on the Explainability of Supervised Machine Learning
  • 3
  • PDF
Achieving Explainability of Intrusion Detection System by Hybrid Oracle-Explainer Approach
  • 1
  • PDF
An Empirical Evaluation of AI Deep Explainable Tools
Underspecification Presents Challenges for Credibility in Modern Machine Learning
  • 33
  • PDF
Decision Explanation: Applying Contextual Importance and Contextual Utility in Affect Detection
  • 1
  • PDF
...
1
2
...

References

SHOWING 1-3 OF 3 REFERENCES
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
  • 4,214
  • Highly Influential
  • PDF
Doctor AI: Predicting Clinical Events via Recurrent Neural Networks
  • 546
  • Highly Influential
  • PDF
Anchors: High-Precision Model-Agnostic Explanations
  • 531
  • Highly Influential
  • PDF