Verifying Explanatory Methods
Principal Investigator
Name
Thomas Lukasiewicz
Degrees
Ph.D.
Institution
University of Oxford
Position Title
Professor
Email
About this CDAS Project
Study
PLCO
(Learn more about this study)
Project ID
PLCO-638
Initial CDAS Request Approval
Jun 18, 2020
Title
Verifying Explanatory Methods
Summary
Deep learning is a field in artificial intelligence that has been showing revolutionary success in many domains. However, the decision-making processes of deep learning models are currently not human-interpretable. Hence, many explanatory methods are being designed with the goal of explaining these models. The PCLO dataset has been used by works in the field of explanatory methods (e.g., https://openreview.net/pdf?id=BJg_roAcK7). Our goal is to verify the faithfulness with which these explanatory methods explain models applied to the medical domain. Having access to the PLCO dataset would be essential to our goal.
Aims
* Verifying the correctness of explanatory methods in artificial intelligence
Collaborators
Eleonora Giunchiglia, University of Oxford
Jakob Foerster, University of Toronto
Thomas Lukasiewicz, University of Oxford
Phil Blunsom, University of Oxford