Charles P. Rizzo and James S. Plank

September, 2024

Published on arXiv.

https://arxiv.org/abs/2409.14298

View Article

Abstract

DBSCAN is an algorithm that performs clustering in the presence of noise. In this paper, we provide two constructions that allow DBSCAN to be implemented neuromorphically, using spiking neural networks. The first construction is termed “flat,” resulting in large spiking neural networks that compute the algorithm quickly, in five timesteps. Moreover, the networks allow pipelining, so that a new DBSCAN calculation may be performed every timestep. The second construction is termed “systolic”, and generates much smaller networks, but requires the inputs to be spiked in over several timesteps, column by column. We provide precise specifications of the constructions and analyze them in practical neuromorphic computing settings. We also provide an open-source implementation.

Citation Information

Text

author        C. P. Rizzo and J. S. Plank 
title         A Neuromorphic Implementation of the {DBSCAN} Algorithm 
year          2024 
eprint        2409.14298
archivePrefix arXiv
primaryClass  cs.NE
url           arXiv:2409.14298
howpublished  https://arxiv.org/abs/2409.14298

Bibtex

@MISC{rp:24:ani,
    author = "C. P. Rizzo and J. S. Plank",
    title = "A Neuromorphic Implementation of the {DBSCAN} Algorithm",
    year = "2024 ",
    eprint = "2409.14298",
    archivePrefix = "arXiv",
    primaryClass = "cs.NE",
    howpublished = "arXiv:2409.14298",
    url = "https://arxiv.org/abs/2409.14298"
}