Scalable Convex Neural Networks: a package for fasts convex optimization of shallow neural networks.
Project description
scnn
: Scalable Convex Neural Networks
A library for global optimization of shallow neural networks. API documentation at ReadTheDocs.
Requirements
Python 3.8 or newer. Development dependencies are listed in dev_requirements.txt
.
Setup
Clone the repository using
git clone https://github.com/pilancilab/scnn.git
Contributions
Coming soon!
Citation
Please cite our paper if you use this package.
@article{DBLP:journals/corr/abs-2202-01331,
author = {Aaron Mishkin and
Arda Sahiner and
Mert Pilanci},
title = {Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model
Classes and Cone Decompositions},
journal = {CoRR},
volume = {abs/2202.01331},
year = {2022},
url = {https://arxiv.org/abs/2202.01331},
}
Looking for the code to replicate our experiments? See scnn_experiments.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
pyscnn-0.0.1b0-py3-none-any.whl
(123.0 kB
view hashes)