Explaining Explanation, Part 4: A Deep Dive on Deep Nets

By Robert R. Hoffman, Tim Miller, Shane T. Mueller, Gary Klein, William J. Clancey. 2018

56 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Safety Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety Research

Citations in the corpus

Counterfactuals in Explainable Artificial Intelligence (XAI): Evidence from Human Reasoning (2019, neutral): “An interpretable model allows a human user to mentally simulate some aspects of the system, and to understand the causes of its decisionmaking [Hoffman et al., 2018].”
Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, background): “tions. Their restricted set of nine queries (of the why and why not forms) are resonant to the notion that there is a limited set of "triggers" that motivate users to seek explanations. See Hoffman, et al. (2018). Kulesza, et al (2015). See also Kulesza, et al, 2010; Kulesza, Stumpf, et al”
DARPA's Explainable Artificial Intelligence (XAI) Program (2019, methodology): “This methodology was described in a series of essays (Hoffman and Klein 2017; Hoffman et al. 2017; Klein 2018; Hoffman et al. 2018).”
A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems (2018, background): “dentified purposes and patterns for causal reasoning [83, 84, 102]. They lastly focus on deep neural networks (DNN) to examine their theoretical and empirical findings on a machine learning algorithm [79]. In other work, they presented a conceptual model of the process of explaining in the XAI conte”
Designing Theory-Driven User-Centric Explainable AI (2019, background): “[40, 41, 42] and Klein [52] summarized several theoretical foundations of how people formulate”