Eliciting knowledge from domain experts can play an important role throughout the machine
learning process, from correctly specifying the task to evaluating model results. However …

At its core, this thesis aims to enhance the practicality of deep learning by improving the
label and training efficiency of deep learning models. To this end, we investigate data subset …

Autism spectrum disorder (ASD) is a neurodevelopmental condition that affects social
communication and behavior. Diagnosing ASD as early as possible is desirable because …

A central concern in an interactive intelligent system is optimization of its actions, to be
maximally helpful to its human user. In recommender systems for instance, the action is to …

We present a human-in-the-loop approach to generate counterfactual (CF) explanations that
preserve global and local feasibility constraints. Global feasibility constraints refer to the …

In healthcare, training examples are usually hard to obtain (eg, cases of a rare disease), or
the cost of labelling data is high. With a large number of features () be measured in a …

While machine learning has shown success in many fields, it can be challenging when there
are limitations with insufficient training data. By incorporating knowledge into the machine …

This thesis develops human-in-the-loop machine learning methods that aim at improving the
performance of a machine learning model in precision medicine tasks. Many problems in …

Unsupervised anomaly detection techniques can extract from data a wealth of information
about unusual events. While this information can at times offer valuable insights on critical …