Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sristi, Ram Dyuthi, Narasimha, Sowmya Manojna, Huang, Jingya, Despatin, Alice, Musall, Simon, Gilja, Vikash, Mishne, Gal
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.20068
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915571493240832
author Sristi, Ram Dyuthi
Narasimha, Sowmya Manojna
Huang, Jingya
Despatin, Alice
Musall, Simon
Gilja, Vikash
Mishne, Gal
author_facet Sristi, Ram Dyuthi
Narasimha, Sowmya Manojna
Huang, Jingya
Despatin, Alice
Musall, Simon
Gilja, Vikash
Mishne, Gal
contents Simultaneous recordings from thousands of neurons across multiple brain areas reveal rich mixtures of activity that are shared between regions and dynamics that are unique to each region. Existing alignment or multi-view methods neglect temporal structure, whereas dynamical latent variable models capture temporal dependencies but are usually restricted to a single area, assume linear read-outs, or conflate shared and private signals. We introduce the Coupled Transformer Autoencoder (CTAE) - a sequence model that addresses both (i) non-stationary, non-linear dynamics and (ii) separation of shared versus region-specific structure in a single framework. CTAE employs transformer encoders and decoders to capture long-range neural dynamics and explicitly partitions each region's latent space into orthogonal shared and private subspaces. We demonstrate the effectiveness of CTAE on two high-density electrophysiology datasets with simultaneous recordings from multiple regions, one from motor cortical areas and the other from sensory areas. CTAE extracts meaningful representations that better decode behavioral variables compared to existing approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20068
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Coupled Transformer Autoencoder for Disentangling Multi-Region Neural Latent Dynamics
Sristi, Ram Dyuthi
Narasimha, Sowmya Manojna
Huang, Jingya
Despatin, Alice
Musall, Simon
Gilja, Vikash
Mishne, Gal
Machine Learning
Simultaneous recordings from thousands of neurons across multiple brain areas reveal rich mixtures of activity that are shared between regions and dynamics that are unique to each region. Existing alignment or multi-view methods neglect temporal structure, whereas dynamical latent variable models capture temporal dependencies but are usually restricted to a single area, assume linear read-outs, or conflate shared and private signals. We introduce the Coupled Transformer Autoencoder (CTAE) - a sequence model that addresses both (i) non-stationary, non-linear dynamics and (ii) separation of shared versus region-specific structure in a single framework. CTAE employs transformer encoders and decoders to capture long-range neural dynamics and explicitly partitions each region's latent space into orthogonal shared and private subspaces. We demonstrate the effectiveness of CTAE on two high-density electrophysiology datasets with simultaneous recordings from multiple regions, one from motor cortical areas and the other from sensory areas. CTAE extracts meaningful representations that better decode behavioral variables compared to existing approaches.
title Coupled Transformer Autoencoder for Disentangling Multi-Region Neural Latent Dynamics
topic Machine Learning
url https://arxiv.org/abs/2510.20068