Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference
This work addresses a domain-specific problem for neuroscience researchers by providing a scalable method for spike source localization, though it is incremental as it builds on existing Bayesian and variational inference techniques.
The authors tackled the problem of localizing neuron positions from extracellular recordings by developing a Bayesian model with amortized variational inference, achieving more accurate results than heuristic methods like center of mass and improving spike sorting performance.
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.