iBCM: Interactive Bayesian Case Model Empowering Humans via Intuitive Interaction

By Been Kim, Elena L. Glassman, Brittney Johnson, Julie Arnold Shah. 2015

55 citations recorded by the source corpus.

How researchers see this paper

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

In Human-Computer Interaction

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “We now synthesize and enumerate deﬁnitions for these XAI goals, so as to settle a ﬁrst classiﬁcation criteria for the full suit of papers covered in this review: • Trustworthiness: Several authors agree upon the search for trustwor-thiness as the primary aim of an explainable AI model [31,32] .”
The mythos of model interpretability (2016, background): “Informativeness: Sometimes machine learning doesn’t directly take actions, but instead provides assistance to human decision makers, a setting considered by Kim et al. (2015); Huysmans et al. (2011).”
A Survey of Methods for Explaining Black Box Models (2018, background): “ Possible drawbacks of this approach are the high number of parameters (e.g., number of clusters) and various types of probability distributions which are assumed to be correct for each type of data. [42] proposes an extension of BCM which exploits humans interaction to improve the prototypes. Final”
SmoothGrad: removing noise by adding noise (2017, background): “, 2012) to education (Kim et al., 2015), there are many domains where interpretability is important.”
Model-Agnostic Interpretability of Machine Learning (2016, methodology): “Using a white box makes it easier to incorporate user feedback in systems like iBCM (Kim et al., 2015), or injecting logic into matrix factorization (Rocktaschel et al., 2015).”
How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation (2018, methodology): “Common types of explanation include regressions with simple, human-simulatable functions [Caruana et al., 2015, Kim et al., 2015a, R¨uping, 2006, Bucilu et al., 2006, Ustun and Rudin, 2016, Doshi-Velez et al., 2015, Kim et al., 2015b, Krakovna and Doshi-Velez, 2016, Hughes et al., 2016, Jung et…”
The relationship between trust in AI and trustworthy machine learning technologies (2019, background): “Explainability refers to relating the operation and outcomes of the model into understandable terms to a human [51].”
Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda (2018, methodology): “gories of interpretable models [91]: sparse linear classifiers [146, 160], discretization methods such as decision trees and association rule lists [103, 110], and instance- or case-based models [92, 94].”
A Review of User Interface Design for Interactive Machine Learning (2018, background): “Kim et al. (2015b) compare a variety of machine learning techniques to the task of document feature compression.”
Human-Centered Tools for Coping with Imperfect Algorithms During Medical Decision-Making (2019, methodology): “Based on this observation, and informed by prior work [24, 47], we allow users to adjust the presence of any concept by picking a subset of search results as examples, and updating results on-the-fly to find more images like those examples.”
Towards A Rigorous Science of Interpretable Machine Learning (2017, background): “…interpretability in the context of an application: if the system is useful in either a practical application or a simpliﬁed version of it, then it must be somehow interpretable (e.g. Ribeiro et al. [2016], Lei et al. [2016], Kim et al. [2015a], Doshi-Velez et al. [2015], Kim et al. [2015b]).”