Examining multiple potential models in end-user interactive concept learning

By Saleema Amershi, James A. Fogarty, Ashish Kapoor, Desney S. Tan. 2010

50 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 Artificial Intelligence

Citations in the corpus

Towards Better Analysis of Deep Convolutional Neural Networks (2016, background): “In the field of visual analytics, researchers have developed interactive image classification systems [3, 47, 51].”
Principles of Explanatory Debugging to Personalize Interactive Machine Learning (2015, background): “…have explored using this cycle of quick interactions to train instance-based classiﬁers [5, 13], enable better model selection by end users [2, 12, 40], elicit labels for the most important instances (e.g., active learning) [7, 37], and to improve reinforcement learning for automated…”
The Role of Explanations in Assessing and Correcting Personalized Intelligent Agents (2012, background): “Recent research has made inroads into supporting this type of functionality [1, 2, 5, 7], but debugging can be difficult for even trained software developers—helping end users, who have knowledge of neither software engineering nor machine learning, is no trivial task.”
A Review of User Interface Design for Interactive Machine Learning (2018, methodology): “In constructing and refining a model, users require the ability to retrace steps in the event that recent actions have resulted in an undesired outcome (Talbot et al. 2009; Kapoor et al. 2010; Amershi et al. 2010).”
Human model evaluation in interactive supervised learning (2011, methodology): “[3], that interactive machine learning interfaces must not only enable the user to effectively edit the training data, but also supply him with the information he needs to most effectively guide the machine learning process.”
Tell me more?: the effects of mental model soundness on personalizing an intelligent agent (2012, background): “Recent research has made inroads into supporting this type of functionality [1,11,14,16].”
No Explainability without Accountability: An Empirical Study of Explanations and Feedback in Interactive ML (2020, background): “Relationship of Explainability and Interactivity in ML Users need to understand how models work [23, 5, 34] to best fix them, and how models are explained changes user feedback [52, 33].”
Power to the People: The Role of Humans in Interactive Machine Learning (2014, background): “The stream of questions also led to a decline in the user’s mental model of how the robot learned, causing some participants to "turn their brain off" or "lose track of what they were teaching" (according to their self report) (Cakmak et al. 2010).”