no code implementations • 29 Jun 2020 • Hugh Chen, Joseph D. Janizek, Scott Lundberg, Su-In Lee
Furthermore, we argue that the choice comes down to whether it is desirable to be true to the model or true to the data.
2 code implementations • 10 Feb 2020 • Joseph D. Janizek, Pascal Sturmfels, Su-In Lee
Integrated Hessians overcomes several theoretical limitations of previous methods to explain interactions, and unlike such previous methods is not limited to a specific architecture or class of neural network.
1 code implementation • 13 Jan 2020 • Joseph D. Janizek, Gabriel Erion, Alex J. DeGrave, Su-In Lee
In order for these models to be safely deployed, we would like to ensure that they do not use confounding variables to make their classification, and that they will work well even when tested on images from hospitals that were not included in the training data.
3 code implementations • ICLR 2020 • Gabriel Erion, Joseph D. Janizek, Pascal Sturmfels, Scott Lundberg, Su-In Lee
Recent research has demonstrated that feature attribution methods for deep networks can themselves be incorporated into training; these attribution priors optimize for a model whose attributions have certain desirable properties -- most frequently, that particular features are important or unimportant.