Research

Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference

Deep Learning

Authors

Published on

05/29/2019

Determining the positions of neurons in an extracellular recording is useful for investigating functional properties of the underlying neural circuitry. In this work, we present a Bayesian modelling approach for localizing the source of individual spikes on high-density, microelectrode arrays. To allow for scalable inference, we implement our model as a variational autoencoder and perform amortized variational inference. We evaluate our method on both biophysically realistic simulated and real extracellular datasets, demonstrating that it is more accurate than and can improve spike sorting performance over heuristic localization methods such as center of mass.

Please cite our work using the BibTeX below.

@article{Hurwitz_2019,
   title={Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference},
   url={http://dx.doi.org/10.1101/656389},
   DOI={10.1101/656389},
   publisher={Cold Spring Harbor Laboratory},
   author={Hurwitz, Cole L. and Xu, Kai and Srivastava, Akash and Buccino, Alessio P. and Hennig, Matthias H.},
   year={2019},
   month={May}
}
Close Modal