Work

Stimulus symmetries can confound representational similarity analyses

Year: 2026

Type: preprint

Abstract: What can representational similarity matrices (RSMs) tell us about a neural code? As the popularity of these summary statistics grows, so too does the need for a more complete characterization of their properties. Here, we show that symmetries in network inputs can confound RSM-based analyses. Stimulus symmetries render many representations functionally equivalent, but these different configurations can lead to different RSMs. These different RSMs reflect qualitatively different representational geometries. We show that stochastic gradient descent or energetic regularization can generate sparse, drifting codes, leading in turn to drifting RSMs. Moreover, we demonstrate that these phenomena are present in networks trained to encode image data, where the symmetry is latent. Our results illustrate the challenges inherent in comparing nonlinear neural codes, when functionally-equivalent representations are not related by a simple rotation.

Source: PubMed

DOI: 10.48550/arxiv.2605.21324

Authors: Pashakhanloo, Farhad, Zavatone-Veth, Jacob A.

Institution: Harvard University Press

Language: English

Topic: Neural Networks and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Institutes of Health, Society of Fellows, Harvard University

Award: Understanding data-driven models for neural dynamics

OpenAlex ID: W7162039974

Cites:

Cited by:

Related to: 10