English

Towards Deep Physical Reservoir Computing Through Automatic Task Decomposition And Mapping

Machine Learning 2019-10-30 v1 Emerging Technologies Neural and Evolutionary Computing Signal Processing

Abstract

Photonic reservoir computing is a promising candidate for low-energy computing at high bandwidths. Despite recent successes, there are bounds to what one can achieve simply by making photonic reservoirs larger. Therefore, a switch from single-reservoir computing to multi-reservoir and even deep physical reservoir computing is desirable. Given that backpropagation can not be used directly to train multi-reservoir systems in our targeted setting, we propose an alternative approach that still uses its power to derive intermediate targets. In this work we report our findings on a conducted experiment to evaluate the general feasibility of our approach by training a network of 3 Echo State Networks to perform the well-known NARMA-10 task using targets derived through backpropagation. Our results indicate that our proposed method is well-suited to train multi-reservoir systems in a efficient way.

Keywords

Cite

@article{arxiv.1910.13332,
  title  = {Towards Deep Physical Reservoir Computing Through Automatic Task Decomposition And Mapping},
  author = {Matthias Freiberger and Peter Bienstman and Joni Dambre},
  journal= {arXiv preprint arXiv:1910.13332},
  year   = {2019}
}

Comments

Submitted to the IEEE International Conference on Rebooting Computing 2019; accepted as a poster, will not be presented though

R2 v1 2026-06-23T11:58:29.093Z