Synthesizing realistic neural population activity patterns using Generative Adversarial Networks

TL;DR

This paper introduces Spike-GAN, a novel generative model based on Wasserstein-GANs, capable of synthesizing realistic neural spike train patterns that match complex statistical properties without prior specification, aiding neuroscience research.

Contribution

Spike-GAN is a flexible, unsupervised generative model that accurately replicates neural population activity and identifies key statistical features without predefined constraints.

Findings

Spike-GAN matches first- and second-order statistics of neural data.

It performs comparably to maximum entropy and Gaussian models.

Spike-GAN can identify important statistical structures in spike trains.

Abstract

The ability to synthesize realistic patterns of neural activity is crucial for studying neural information processing. Here we used the Generative Adversarial Networks (GANs) framework to simulate the concerted activity of a population of neurons. We adapted the Wasserstein-GAN variant to facilitate the generation of unconstrained neural population activity patterns while still benefiting from parameter sharing in the temporal domain. We demonstrate that our proposed GAN, which we termed Spike-GAN, generates spike trains that match accurately the first- and second-order statistics of datasets of tens of neurons and also approximates well their higher-order statistics. We applied Spike-GAN to a real dataset recorded from salamander retina and showed that it performs as well as state-of-the-art approaches based on the maximum entropy and the dichotomized Gaussian frameworks. Importantly, Spike-GAN does not require to specify a priori the statistics to be matched by the model, and so constitutes a more flexible method than these alternative approaches. Finally, we show how to exploit a trained Spike-GAN to construct 'importance maps' to detect the most relevant statistical structures present in a spike train. Spike-GAN provides a powerful, easy-to-use technique for generating realistic spiking neural activity and for describing the most relevant features of the large-scale neural population recordings studied in modern systems neuroscience.