Search Results for author: William Knauth

Found 2 papers, 1 papers with code

The Self-Simplifying Machine: Exploiting the Structure of Piecewise Linear Neural Networks to Create Interpretable Models

no code implementations • 2 Dec 2020 • William Knauth

Today, it is more important than ever before for users to have trust in the models they use.

Paper
Add Code

Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplification

1 code implementation • 8 Nov 2020 • Agus Sudjianto, William Knauth, Rahul Singh, Zebin Yang, Aijun Zhang

We propose the local linear profile plot and other visualization methods for interpretation and diagnostics, and an effective merging strategy for network simplification.

871

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.