C. D. Schuman and C. P. Rizzo and G. S. Rose and J. S. Plank

April, 2024

Neuro-Inspired Computational Elements Conference

https://ieeexplore.ieee.org/document/10548512

PDF not available yet, or is only available from the conference/journal publisher.

Abstract

Recurrent, sparse spiking neural networks have been explored in contexts such as reservoir computing and winner-take-all networks. However, we believe there is the opportunity to leverage recurrence in spiking neural networks for other tasks, particularly for control. In this work, we show that evolved recurrent neural networks perform significantly better than feed-forward counterparts. We give two examples of the types of recurrent networks that are evolved and demonstrate that they are highly recurrent and unlike traditional, more structured recurrent neural networks that are used in deep learning literature.

Citation Information

Text

author      C. D. Schuman and C. P. Rizzo and G. S. Rose and J. S. Plank
title       Embracing the Hairball: An Investigation of Recurrence in Spiking Neural Networks for Control
booktitle   NICE: Neuro-Inspired Computational Elements Workshop
year        2024
month       April
doi         10.1109/NICE61972.2024.10548512
url         https://ieeexplore.ieee.org/document/10548512/

Bibtex

@INPROCEEDINGS{srr:24:eh,
    author = "C. D. Schuman and C. P. Rizzo and G. S. Rose and J. S. Plank",
    title = "Embracing the Hairball: An Investigation of Recurrence in Spiking Neural Networks for Control",
    booktitle = "NICE: Neuro-Inspired Computational Elements Workshop",
    year = "2024",
    month = "April",
    doi = "10.1109/NICE61972.2024.10548512",
    url = "https://ieeexplore.ieee.org/document/10548512/"
}