Dec 7, 2022 · In this work, we propose a Self-Explaining Selective Model (SESM) that uses a linear combination of prototypical concepts to explain its own predictions.

Prototype-based interpretability methods provide intuitive explanations of model prediction by comparing samples to a reference set of memorized exemplars or ...

Feb 7, 2023 · In this work, we propose a Self-Explaining Selective Model (SESM) that uses a linear combination of prototypical concepts to explain its own predictions.

Prototype-based interpretability methods provide intuitive explanations of model prediction by comparing samples to a reference set of memorized exemplars or ...

Code for "Learning to Select Prototypical Parts for Interpretable Sequential Data Modeling" in Proc. of AAAI'23. The code was attached as a technical ...

Prototype methods aim to select a relatively small number of samples from a data set which, if well chosen, can serve as a summary of the original data set. In ...

In this work, we have devised a framework for evaluating the interpretability of part-prototype-based models from a human perspective that solves these issues. ...

Sep 6, 2024 · The prediction is obtained by comparing the inputs to a few prototypes, which are exemplar cases in the problem domain. For better ...

Learning to Select Prototypical Parts for Interpretable Sequential Data Modeling · Prediction With Visual Evidence: Sketch Classification Explanation via Stroke- ...

We propose a novel method, ProtoAttend, for selecting input-dependent prototypes based on an attention mechanism between the input and prototype candidates.