Skip to content
Interpreting neural networks by reducing nonlinearities during training
TeX Lua HTML Perl
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
code
.gitignore
LICENSE
README.md
example.png
linearize.tex

README.md

Interpreting Neural Networks by Reducing Nonlinearities during Training

This repo contains a short paper and sample code demonstrating a simple solution that makes it possible to extract rules from a neural network that employs Parametric Rectified Linear Units (PReLUs). We introduce a force, applied in parallel to backpropagation, that aims to reduce PReLUs into the identity function, which then causes the neural network to collapse into a smaller system of linear functions and inequalities suitable for review or use by human decision makers.

As this force reduces the capacity of neural networks, it is expected to help avoid overfitting as well.

Download the article in PDF format from the latest release at https://github.com/csirmaz/trained-linearization/releases/latest .

You can’t perform that action at this time.