Machine learning plays a role in many deployed decision systems, often in ways that are
difficult or impossible to understand by human stakeholders. Explaining, in a human …

We study neural network loss landscapes through the lens of mode connectivity, the
observation that minimizers of neural networks retrieved via training on a dataset are …

Counterfactual explanations have shown promising results as a post-hoc framework to make
image classifiers more explainable. In this paper, we propose DiME, a method allowing the …

In recent years, remarkable achievements have been made in artificial intelligence tasks
and applications based on deep neural networks (DNNs), especially in the fields of vision …

Counterfactual explanations and adversarial attacks have a related goal: flipping output
labels with minimal perturbations regardless of their characteristics. Yet, adversarial attacks …

Abstract Machine learning (ML) models are typically optimized for their accuracy on a given
dataset. However, this predictive criterion rarely captures all desirable properties of a model …

Accessible rapid COVID-19 testing continues to be necessary and several studies involving
deep neural network (DNN) methods for detection have been published. As part of a …

Attribution-based explanations are popular in computer vision but of limited use for fine-
grained classification problems typical of expert domains, where classes differ by subtle …

Counterfactual explanations have emerged as a promising method for elucidating the
behavior of opaque black-box models. Recently, several works leveraged pixel-space …

Combinatorial generalization refers to the ability to collect and assemble various attributes
from diverse data to generate novel unexperienced data. This ability is considered a …