-
FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging
Influence functions approximate the 'influences' of training data-points...
12/31/2020 ∙ by Han Guo, et al. ∙
9
∙
share
read it
-
Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?
Data collection for natural language (NL) understanding tasks has increa...
10/08/2020 ∙ by Peter Hase, et al. ∙
7
∙
share
read it
-
Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?
Algorithmic approaches to interpreting machine learning models have prol...
05/04/2020 ∙ by Peter Hase, et al. ∙
98
∙
share
read it
-
Interpretable Image Recognition with Hierarchical Prototypes
Vision models are interpretable when they classify objects on the basis ...
06/25/2019 ∙ by Peter Hase, et al. ∙
2
∙
share
read it
-
Shall I Compare Thee to a Machine-Written Sonnet? An Approach to Algorithmic Sonnet Generation
We provide code that produces beautiful poetry. Our sonnet-generation al...
11/13/2018 ∙ by John Benhart, et al. ∙
0
∙
share
read it
Peter Hase
verfied profile
∙
0
followers
Duke University
∙
University of North Carolina at Chapel Hill
