Explaining Predictions from Machine Learning Models: Algorithms, Users, and Pedagogy
It tackles the explainability problem for users affected by algorithmic predictions, with incremental contributions across multiple aspects.
The thesis addresses the problem of machine learning model explainability by examining it from algorithmic, user, and pedagogical perspectives, contributing novel solutions to help users understand and potentially change predictions.
Model explainability has become an important problem in machine learning (ML) due to the increased effect that algorithmic predictions have on humans. Explanations can help users understand not only why ML models make certain predictions, but also how these predictions can be changed. In this thesis, we examine the explainability of ML models from three vantage points: algorithms, users, and pedagogy, and contribute several novel solutions to the explainability problem.