Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity
Abstract
Meaningful and simplified representations of neural activity can yield insights into how and what information is being processed within a neural circuit. However, without labels, finding representations that reveal the link between the brain and behavior can be challenging. Here, we introduce a novel unsupervised approach for learning disentangled representations of neural activity called Swap-VAE. Our approach combines a generative modeling framework with an instance-specific alignment loss that tries to maximize the representational similarity between transformed views of the input (brain state). These transformed (or augmented) views are created by dropping out neurons and jittering samples in time, which intuitively should lead the network to a representation that maintains both temporal consistency and invariance to the specific neurons used to represent the neural state. Through evaluations on both synthetic data and neural recordings from hundreds of neurons in different primate brains, we show that it is possible to build representations that disentangle neural datasets along relevant latent dimensions linked to behavior.
Cite
@article{arxiv.2111.02338,
title = {Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity},
author = {Ran Liu and Mehdi Azabou and Max Dabagia and Chi-Heng Lin and Mohammad Gheshlaghi Azar and Keith B. Hengen and Michal Valko and Eva L. Dyer},
journal= {arXiv preprint arXiv:2111.02338},
year = {2021}
}
Comments
To be published in Neurips 2021