K. Patel, L. Whatley, B. Gullett, J. Mowry, S. N. B. Tushar, S. H. Alam, C. Rizzo, G. Rose, A. Young, J. S. Plank and C. D. Schuman

August, 2026

ICONS: International Conference on Neuromorphic Systems

https://dl.acm.org/doi/10.1145/3822454.3822469

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

Abstract

Surrogate gradient methods have emerged as the dominant approach for enabling backpropagation for spiking neural networks (SNNs). However, many implementations are tightly coupled to target hardware platforms, constraining flexibility. In this work, we present a flexible, end-to-end workflow for the training, optimization, and deployment of SNNs across multiple neuromorphic hardware systems, with an emphasis on extensibility to future neuromorphic platforms. Our API integrates a modified implementation of SLAYER, a popular surrogate gradient descent approach, within the TENNLab neuromorphic software framework. We evaluate this workflow across multiple datasets, achieving competitive performance with state-of-the-art results, and we report energy metrics on custom neuromorphic hardware platforms.

Citation Information

Text

author      K. Patel and L. Whatley and B. Gullett and J. Mowry and S. N. B. Tushar
            and S. H. Alam and C. Rizzo and G. Rose and A. Young and J. S. Plank 
            and C. D. Schuman
title       A Neuromorphic Pipeline from Training to Hardware Deployment Using {SLAYER}
booktitle   International Conference on Neuromorphic Systems (ICONS)
year        2026
url         https://dl.acm.org/doi/10.1145/3822454.3822469
doi         10.1145/3822454.3822469
pages       165-172

Bibtex

@INPROCEEDINGS{pwg:26:anp,
    author = "K. Patel and L. Whatley and B. Gullett and J. Mowry and S. N. B. Tushar
                and S. H. Alam and C. Rizzo and G. Rose and A. Young and J. S. Plank 
                and C. D. Schuman",
    title = "A Neuromorphic Pipeline from Training to Hardware Deployment Using {SLAYER}",
    booktitle = "International Conference on Neuromorphic Systems (ICONS)",
    year = "2026",
    url = "https://dl.acm.org/doi/10.1145/3822454.3822469",
    doi = "10.1145/3822454.3822469",
    pages = "165-172"
}