Picture for William Knauth

William Knauth

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

Add code
Dec 02, 2020
Figure 1 for The Self-Simplifying Machine: Exploiting the Structure of Piecewise Linear Neural Networks to Create Interpretable Models
Figure 2 for The Self-Simplifying Machine: Exploiting the Structure of Piecewise Linear Neural Networks to Create Interpretable Models
Figure 3 for The Self-Simplifying Machine: Exploiting the Structure of Piecewise Linear Neural Networks to Create Interpretable Models
Figure 4 for The Self-Simplifying Machine: Exploiting the Structure of Piecewise Linear Neural Networks to Create Interpretable Models
Viaarxiv icon

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

Add code
Nov 08, 2020
Figure 1 for Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplification
Figure 2 for Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplification
Figure 3 for Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplification
Figure 4 for Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplification
Viaarxiv icon