A Random Matrix Approach to Echo-State Neural Networks

Abstract

Recurrent neural networks, especially in their linear version, have provided many qualitative insights on their performance under different configurations. This article provides, through a novel random matrix framework, the quantitative counterpart of these performance results, specifically in the case of echo-state networks. Beyond mere insights, our approach conveys a deeper understanding on the core mechanism under play for both training and testing.

Cite

Text

Couillet et al. "A Random Matrix Approach to Echo-State Neural Networks." International Conference on Machine Learning, 2016.

Markdown

[Couillet et al. "A Random Matrix Approach to Echo-State Neural Networks." International Conference on Machine Learning, 2016.](https://mlanthology.org/icml/2016/couillet2016icml-random/)

BibTeX

@inproceedings{couillet2016icml-random,
  title     = {{A Random Matrix Approach to Echo-State Neural Networks}},
  author    = {Couillet, Romain and Wainrib, Gilles and Ali, Hafiz Tiomoko and Sevi, Harry},
  booktitle = {International Conference on Machine Learning},
  year      = {2016},
  pages     = {517-525},
  volume    = {48},
  url       = {https://mlanthology.org/icml/2016/couillet2016icml-random/}
}