Learning Time-Scale Invariant Population-Level Neural Representations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Patel, Eshani, Yue, Yisong, Chau, Geeling
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911269715443712
author Patel, Eshani
Yue, Yisong
Chau, Geeling
author_facet Patel, Eshani
Yue, Yisong
Chau, Geeling
contents General-purpose foundation models for neural time series can help accelerate neuroscientific discoveries and enable applications such as brain computer interfaces (BCIs). A key component in scaling these models is population-level representation learning, which leverages information across channels to capture spatial as well as temporal structure. Population-level approaches have recently shown that such representations can be both efficient to learn on top of pretrained temporal encoders and produce useful representations for decoding a variety of downstream tasks. However, these models remain sensitive to mismatches in preprocessing, particularly on time-scales, between pretraining and downstream settings. We systematically examine how time-scale mismatches affects generalization and find that existing representations lack invariance. To address this, we introduce Time-scale Augmented Pretraining (TSAP), which consistently improves robustness to different time-scales across decoding tasks and builds invariance in the representation space. These results highlight handling preprocessing diversity as a key step toward building generalizable neural foundation models.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13022
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Time-Scale Invariant Population-Level Neural Representations
Patel, Eshani
Yue, Yisong
Chau, Geeling
Machine Learning
General-purpose foundation models for neural time series can help accelerate neuroscientific discoveries and enable applications such as brain computer interfaces (BCIs). A key component in scaling these models is population-level representation learning, which leverages information across channels to capture spatial as well as temporal structure. Population-level approaches have recently shown that such representations can be both efficient to learn on top of pretrained temporal encoders and produce useful representations for decoding a variety of downstream tasks. However, these models remain sensitive to mismatches in preprocessing, particularly on time-scales, between pretraining and downstream settings. We systematically examine how time-scale mismatches affects generalization and find that existing representations lack invariance. To address this, we introduce Time-scale Augmented Pretraining (TSAP), which consistently improves robustness to different time-scales across decoding tasks and builds invariance in the representation space. These results highlight handling preprocessing diversity as a key step toward building generalizable neural foundation models.
title Learning Time-Scale Invariant Population-Level Neural Representations
topic Machine Learning
url https://arxiv.org/abs/2511.13022