Linear Readout of Neural Manifolds with Continuous Variables
Neurons and Cognition
2026-03-12 v1 Disordered Systems and Neural Networks
Abstract
Brains and artificial neural networks compute with continuous variables such as object position or stimulus orientation. However, the complex variability in neural responses makes it difficult to link internal representational structure to task performance. We develop a statistical-mechanical theory of regression capacity that relates linear decoding efficiency of continuous variables to geometric properties of neural manifolds. Our theory handles complex neural variability and applies to real data, revealing increasing capacity for decoding object position and size along the monkey visual stream.
Cite
@article{arxiv.2603.10956,
title = {Linear Readout of Neural Manifolds with Continuous Variables},
author = {Will Slatton and Chi-Ning Chou and SueYeon Chung},
journal= {arXiv preprint arXiv:2603.10956},
year = {2026}
}