How AI detectives are cracking open the black box of deep learning

By P. Voosen. 2017

60 citations recorded by the source corpus.

Subfields: Health Informatics, Information Systems

How researchers see this paper

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

In Health Informatics

1. Nadia Burkart
2. Marco F. Huber

In Information Systems

1. Wil M.P. van der Aalst
2. Nadia Burkart
3. Christof Weinhardt
4. Marco F. Huber
5. Manfred Reichert
6. Bernd Weber
7. Wil van der Aalst
8. Boudewijn van Dongen

Citations in the corpus

• Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, neutral): “…Bell, and Schocken, 2017; Clancey, 1986a; Cooper, 2004; Core, et al., 2006; Harford, 2014; Hawkins, 2017; Kim, 2018; Kuang, 2017; Marcus, 2017; Monroe, 2018; Pavlus, 2017; Nott, 2017; Pinker, 2017; Schwiep, 2017; Sheh and Monteath, 2018; Voosen, 2017; Wang, et al., 2019; Weinberger, 2017).”
• Metrics for Explainable AI: Challenges and Prospects (2018, neutral): “AI systems are receiving considerable attention in the recent popular press (Alang, 2017; Bornstein, 2016; Champlin, Bell & Schocken, 2017; Harford, 2014; Hawkins, 2017; Kuang, 2017; Pavlus, 2017; Pinker, 2017; Schwiep, 2017; Voosen, 2017; Weinberger, 2017).”
• A Survey on the Explainability of Supervised Machine Learning (2020, background): “” Jason Yosinski from Uber states (Voosen, 2017) “We build amazing models.”
• Expl(AI)n It to Me – Explainable AI and Information Systems Research (2021, background): “…are vital to informing fact-based decision-making (regarding disease detection even in a literal sense), the high predictive performance of state-ofthe-art machine learning models generally comes at the expense of transparency and interpretability of their outputs (Voosen 2017; Du et al. 2019).”
• A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability (2018, background): “The goal of Explainable AI [exp, 2018] is to overcome the interpretability problem of AI [Voosen, 2017]; that is, to explain why the AI outputs a specific decision, say to in determining whether to give a loan someone.”