A discrete generative model of neuronal spiking activity on microelectrode arrays
Abstract
Generative models of neural activity could help characterize tissue dynamics, compare experimental conditions, and simulate population activity for applications ranging from disease and drug-response studies to closed-loop experimentation. Existing approaches, however, typically assume a fixed set of sorted neurons, whereas high-density microelectrode arrays produce extremely sparse, array-wide binary spike volumes in which the observed subset of electrodes varies across assays. We introduce a discrete generative model that represents this activity using a shared vocabulary of spatiotemporal motifs. A residual vector-quantized autoencoder learns the motif vocabulary, while a factorized masked transformer predicts where activity occurs and which motif appears at each active location. We evaluate the model on 31 assays spanning human brain organoids and acute \emph{ex vivo} human hippocampal tissue. The learned motifs are broadly reused: assay identity explains only 9% of the entropy in motif use, and motif overlap across tissue types is comparable to overlap within them. When representation quality is evaluated independently of the generative prior, our approach achieves 5.2× the voxel-level reconstruction average precision of a matched flat tokenizer. For masked completion and free generation, the full model achieves $1.4−−2.6\times$ the site-level average precision of the matched generative baseline and outperforms it across all four families of generation metrics. These results establish a compact, reusable representation for array-wide spiking activity without learned assay-specific parameters, providing a scalable foundation for generative modeling across diverse neural preparations.
Related
- Stochastic Dynamics of Large-Scale Motif-Embedded Spiking Neuronal Networks
- Map of spiking activity underlying change detection in the mouse visual system
- Detection of spiking motifs of arbitrary length in neural activity using bounded synaptic delays
- A Neuronal Gene Expression Program Underlying Sustained Network Activity
- Partial sleep deprivation diminishes and uncouples neuronal activity and energy metabolism in the live mouse hippocampus
BibTeX
@misc{tanveer2026discrete,
title = {{A discrete generative model of neuronal spiking activity on microelectrode arrays}},
author = {Md Sayed Tanveer and Mohammed A. Mostajo-Radji and Ge Wang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.23907},
eprint = {2609.23907},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.23907},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - A discrete generative model of neuronal spiking activity on microelectrode arrays
AU - Md Sayed Tanveer
AU - Mohammed A. Mostajo-Radji
AU - Ge Wang
PY - 2026
DA - 2026/09/20
PB - arXiv
DO - 10.48550/arxiv.2609.23907
UR - https://arxiv.org/abs/2609.23907
AB - Generative models of neural activity could help characterize tissue dynamics, compare experimental conditions, and simulate population activity for applications ranging from disease and drug-response studies to closed-loop experimentation. Existing approaches, however, typically assume a fixed set of sorted neurons, whereas high-density microelectrode arrays produce extremely sparse, array-wide binary spike volumes in which the observed subset of electrodes varies across assays. We introduce a discrete generative model that represents this activity using a shared vocabulary of spatiotemporal motifs. A residual vector-quantized autoencoder learns the motif vocabulary, while a factorized masked transformer predicts where activity occurs and which motif appears at each active location. We evaluate the model on 31 assays spanning human brain organoids and acute \emph{ex vivo} human hippocampal tissue. The learned motifs are broadly reused: assay identity explains only 9% of the entropy in motif use, and motif overlap across tissue types is comparable to overlap within them. When representation quality is evaluated independently of the generative prior, our approach achieves 5.2× the voxel-level reconstruction average precision of a matched flat tokenizer. For masked completion and free generation, the full model achieves $1.4−−2.6\times$ the site-level average precision of the matched generative baseline and outperforms it across all four families of generation metrics. These results establish a compact, reusable representation for array-wide spiking activity without learned assay-specific parameters, providing a scalable foundation for generative modeling across diverse neural preparations.
ER -