Experiments on Properties of Hidden Structures of Sparse Neural Networks

This repository contains some accompanying code for reproducing experiments in our article on investigating properties of hidden structures of sparse neural networks. We used and extended deepstruct in this context and refined our understanding of initializing sparse networks with prior structural information.

@inproceedings{stier2021experiments,
  title={Experiments on properties of hidden structures of sparse neural networks},
  author={Stier, Julian and Darji, Harshil and Granitzer, Michael},
  booktitle={International Conference on Machine Learning, Optimization, and Data Science},
  pages={380--394},
  year={2021},
  organization={Springer}
}