Neural Functional Alignment Space: Brain-Referenced Representation of Artificial Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yan, Ruiyu, Jiang, Hanqi, Pan, Yi, Li, Xiaobo, Liu, Tianming, Jiang, Xi, Zhao, Lin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908858651246592
author Yan, Ruiyu
Jiang, Hanqi
Pan, Yi
Li, Xiaobo
Liu, Tianming
Jiang, Xi
Zhao, Lin
author_facet Yan, Ruiyu
Jiang, Hanqi
Pan, Yi
Li, Xiaobo
Liu, Tianming
Jiang, Xi
Zhao, Lin
contents We propose the Neural Functional Alignment Space (NFAS), a brain-referenced representational framework for characterizing artificial neural networks on equal functional grounds. NFAS departs from conventional alignment approaches that rely on layer-wise features or task-specific activations by modeling the intrinsic dynamical evolution of stimulus representations across network depth. Specifically, we model layer-wise embeddings as a depth-wise dynamical trajectory and apply Dynamic Mode Decomposition (DMD) to extract the stable mode. This representation is then projected into a biologically anchored coordinate system defined by distributed neural responses. We also introduce the Signal-to-Noise Consistency Index (SNCI) to quantify cross-model consistency at the modality level. Across 45 pretrained models spanning vision, audio, and language, NFAS reveals structured organization within this brain-referenced space, including modality-specific clustering and cross-modal convergence in integrative cortical systems. Our findings suggest that representation dynamics provide a principled basis for
format Preprint
id arxiv_https___arxiv_org_abs_2603_00793
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neural Functional Alignment Space: Brain-Referenced Representation of Artificial Neural Networks
Yan, Ruiyu
Jiang, Hanqi
Pan, Yi
Li, Xiaobo
Liu, Tianming
Jiang, Xi
Zhao, Lin
Computer Vision and Pattern Recognition
We propose the Neural Functional Alignment Space (NFAS), a brain-referenced representational framework for characterizing artificial neural networks on equal functional grounds. NFAS departs from conventional alignment approaches that rely on layer-wise features or task-specific activations by modeling the intrinsic dynamical evolution of stimulus representations across network depth. Specifically, we model layer-wise embeddings as a depth-wise dynamical trajectory and apply Dynamic Mode Decomposition (DMD) to extract the stable mode. This representation is then projected into a biologically anchored coordinate system defined by distributed neural responses. We also introduce the Signal-to-Noise Consistency Index (SNCI) to quantify cross-model consistency at the modality level. Across 45 pretrained models spanning vision, audio, and language, NFAS reveals structured organization within this brain-referenced space, including modality-specific clustering and cross-modal convergence in integrative cortical systems. Our findings suggest that representation dynamics provide a principled basis for
title Neural Functional Alignment Space: Brain-Referenced Representation of Artificial Neural Networks
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.00793