Thesis
Explaining black box algorithms: epistemological challenges and machine learning solutions
- Abstract:
-
This dissertation seeks to clarify and resolve a number of fundamental issues surrounding algorithmic explainability. What constitutes a satisfactory explanation of a supervised learning model or prediction? What are the basic units of explanation and how do they vary across agents and contexts? Can reliable methods be designed to generate model-agnostic algorithmic explanations? I tackle these questions over the course of eight chapters, examining existing work in interpretable machine le...
Expand abstract
Actions
Authors
Contributors
+ Floridi, L
Institution:
University of Oxford
Division:
SSD
Department:
Oxford Internet Institute
Sub department:
Oxford Internet Institute
Role:
Supervisor
ORCID:
0000-0002-5444-2280
+ Kusner, M
Institution:
University College London
Role:
Supervisor
+ Eberhardt, F
Institution:
Caltech
Role:
Examiner
+ Taddeo, M
Institution:
University of Oxford
Division:
SSD
Department:
Oxford Internet Institute
Sub department:
Oxford Internet Institute
Role:
Examiner
Bibliographic Details
- Type of award:
- DPhil
- Level of award:
- Doctoral
- Awarding institution:
- University of Oxford
Item Description
- Language:
-
English
- Keywords:
- Subjects:
- Deposit date:
-
2021-04-23
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record