Deep learning as performed by artificial deep neural networks (DNNs) has achieved great
successes recently in many important areas that deal with text, images, videos, graphs, and …

Complex machine learning models for NLP are often brittle, making different predictions for
input instances that are extremely similar semantically. To automatically detect this behavior …

Despite widespread adoption, machine learning models remain mostly black boxes.
Understanding the reasons behind predictions is, however, quite important in assessing …

Recent advances in artificial intelligence (AI) have drawn attention to the need for AI systems
to be understandable to human users. The explainable AI (XAI) literature aims to enhance …

As machine learning systems move from computer-science laboratories into the open world,
their accountability becomes a high priority problem. Accountability requires deep …

A rich line of research attempts to make deep neural networks more transparent by
generating human-interpretable'explanations' of their decision process, especially for …

Recent advances in artificial intelligence (AI) have drawn attention to the need for AI systems
to be understandable to human users. The explainable AI (XAI) literature aims to enhance …

Given a pre-trained CNN without any testing samples, this paper proposes a simple yet
effective method to diagnose feature representations of the CNN. We aim to discover …

As robots aspire for long-term autonomous operations in complex dynamic environments,
the ability to reliably take mission-critical decisions in ambiguous situations becomes critical …

Counterfactual (CF) explanations have been employed as one of the modes of explainability
in explainable artificial intelligence (AI)—both to increase the transparency of AI systems …