In a dynamic stream there is an assumption that the underlying process generating the
stream is non-stationary and that concepts within the stream will drift and change as the …

In domains ranging from computer vision to natural language processing, machine learning
models have been shown to exhibit stark disparities, often performing worse for members of …

Deep neural networks are highly susceptible to learning biases in visual data. While various
methods have been proposed to mitigate such bias, the majority require explicit knowledge …

We examine a simple stochastic strategy for adapting well-known single-point acquisition
functions to allow batch active learning. Unlike acquiring the top-K points from the pool set …

This paper addresses and solves some challenges in the adoption of machine learning in
insurance with the democratization of model deployment. The first challenge is reducing the …

Contextual information is a valuable cue for Deep Neural Networks (DNNs) to learn better
representations and improve accuracy. However, co-occurrence bias in the training dataset …

We introduce a new learning framework, Fair Robust Active Learning (FRAL), generalizing
conventional active learning to fair and adversarial robust scenarios. This framework …

Improving the accuracy-fairness frontier of deep neural network (DNN) models is an
important problem. Uncertainty-based active learning (AL) can potentially improve the …

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 …

The fairness of a deep neural network is strongly affected by dataset bias and spurious
correlations, both of which are usually present in modern feature-rich and complex visual …