When stakes are high: Balancing accuracy and transparency with Model-Agnostic Interpretable Data-driven suRRogates

MAGIX: Model Agnostic Globally Interpretable Explanations

Explaining the behavior of a black box machine learning model at the instance level is useful for building trust. However, what is also important is understanding how the model behaves globally. Such an understanding provides insight into both the data on which the model was trained and the generalization power of the rules it learned. We present here an approach that learns rules to explain gl...

Accuracy in Detecting High Stakes

Author(s): Clea Wright Whelan ; Graham Wagstaff ; Jacqueline M Wheatcroft Title: High stakes lies: Police and non-police accuracy in detecting deception Date: 2015. Appeared online 26 June 2014 Originally published in: Psychology, Crime and Law Example citation: Wright Whelan, C., Wagstaff, G., & Wheatcroft, J. M. (2015). High stakes lies: Police and non-police accuracy in detecting deception. ...

Crucial conversations: tools for talking when the stakes are high.

Local Interpretable Model-Agnostic Explanations for Music Content Analysis

The interpretability of a machine learning model is essential for gaining insight into model behaviour. While some machine learning models (e.g., decision trees) are transparent, the majority of models used today are still black-boxes. Recent work in machine learning aims to analyse these models by explaining the basis of their decisions. In this work, we extend one such technique, called local...

Making clinical decisions when the stakes are high and the evidence unclear.

Dylan, a 20 month old boy, was referred to a paediatric allergy clinic for assessment of his peanut allergy. At 12 months of age he developed facial contact urticaria to peanut butter, which spontaneously resolved without respiratory or other symptoms. Since then, he has not had further reactions or eaten peanuts, although the rest of the family often eat peanuts and nuts. Dylan is regularly ca...