Abstract
This document introduces a novel fractal-based connectivity method for Spherical Spiking Neural Networks (SNNs). This approach significantly enhances the initialization and resource efficiency of the network, making it suitable for large-scale models and extending the usability of older hardware. The fractal method can potentially accelerate network setup by up to 50% and improve long-term energy efficiency based on tests on older hardware.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Recommended Citation
Gagnon, Renee, "Fractal-Based Connectivity in Spherical Spiking Neural Networks (SNN)", Technical Disclosure Commons, (July 15, 2024)
https://www.tdcommons.org/dpubs_series/7191
COinS