The reviewed record of science sign in
Pith

arxiv: 2209.03450 · v3 · pith:UX2XJP46 · submitted 2022-09-07 · cs.LG

Seeking Interpretability and Explainability in Binary Activated Neural Networks

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:UX2XJP46record.jsonopen to challenge →

classification cs.LG
keywords activatedbinarynetworksapproachinterpretabilityneuralpredictorstime
0
0 comments X
read the original abstract

We study the use of binary activated neural networks as interpretable and explainable predictors in the context of regression tasks on tabular data; more specifically, we provide guarantees on their expressiveness, present an approach based on the efficient computation of SHAP values for quantifying the relative importance of the features, hidden neurons and even weights. As the model's simplicity is instrumental in achieving interpretability, we propose a greedy algorithm for building compact binary activated networks. This approach doesn't need to fix an architecture for the network in advance: it is built one layer at a time, one neuron at a time, leading to predictors that aren't needlessly complex for a given task.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.