multi-scale-info-geometry-neural

Multi-scale information geometry framework revealing the structure of mutual information in neural populations. A unique Riemannian representational geometry emerges from coarse-graining, extending Fisher information metric to capture encoding structure from fine to coarse stimulus distinctions. Use when researching neural population coding, information geometry, Fisher information in neuroscience, or neural representational geometry. Based on arXiv:2605.06304.

Aller à l'installation

Dépôt: hiyenwong/ai_collection
Dernière activité de la source: 13 juillet 2026 à 02:00
Langue détectée de SKILL.md: anglais
Étoiles: 2
Forks: 0

Options d'installation

Le prompt qui vérifie d'abord la source est sélectionné par défaut. Vous pouvez passer à une commande directe ou télécharger une copie locale.

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Une commande directe contourne le prompt de vérification. Examinez la source avant de l'exécuter.

npx skills add https://github.com/hiyenwong/ai_collection --skill multi-scale-info-geometry-neural

La commande reste sur une seule ligne. Faites défiler horizontalement pour la vérifier avant de la copier.

Vous préférez une copie locale ? Téléchargez les fichiers actuellement disponibles dans SkillsMP.

Vérifiez les fichiers source

Lisez SKILL.md et les fichiers associés affichés par SkillsMP avant de décider de l'installer.

SKILL.md

Instructions source · Aperçu en lecture seule

Retour à la recherche Retour à l’installation

Multi-Scale Information Geometry for Neural Population Analysis

arXiv: 2605.06304 | Authors: Simone Azeglio, Steeve Laquitaine, Ulisse Ferrari, Matthew Chalk

Overview

This paper develops a principled framework connecting information geometry, mutual information, and neural population coding. The authors show that a unique Riemannian representational geometry emerges from first principles governing how distances contract as stimulus resolution is lost through coarse-graining.

Core Problem

Different constructions of representational distances (e.g., Fisher information, decoding-based) can lead to qualitatively different conclusions about the neural code. This ambiguity is resolved by deriving a unique geometry from first principles.

Key Contributions

1. Multi-Scale Fisher Information Metric

Extends classic Fisher information metric to a multi-scale framework
Captures encoding structure from fine stimulus details to coarse global distinctions
Metric tensor can be estimated using diffusion models, making it practical for large neural populations

2. Exact Connection to Mutual Information

The resulting geometry is exactly related to the mutual information encoded by the population
Well-encoded stimulus directions → expanded in this geometry
Poorly-encoded directions → contracted
Provides an interpretable geometric visualization of neural information content

3. Diffusion Model Estimation

Practical estimation method using diffusion models
Scales to high-dimensional stimuli and large populations
Applied to visual cortical responses to natural images

4. Interpretable Features

Eigenvectors of the metric tensor identify stimulus variations contributing most to information transmission
Robust to modelling choices
Applied to visual cortex data revealing meaningful stimulus features

Theoretical Framework

Riemannian Geometry from Coarse-Graining

Define distances in stimulus space based on how reliably stimuli are distinguished from neural activity
As stimulus resolution is lost through coarse-graining, distances contract
A unique geometry emerges from this contraction process — not dependent on arbitrary choices

Multi-Scale Extension

Different scales reveal different aspects of neural encoding
Fine scale: subtle stimulus distinctions
Coarse scale: broad categorical differences
The geometry at each scale is consistent (nested)

Mutual Information Relationship

Metric tensor expansion/contraction directly maps to mutual information contributions
Directions with more Fisher information → higher mutual information contribution
Provides geometric understanding of what the population encodes

Key Results

Unique geometry emerges from first principles of coarse-graining
Geometry directly relates to mutual information: expanded = well-encoded
Diffusion models enable practical estimation for large-scale neural data
Applied to visual cortex: eigenvectors reveal meaningful stimulus features
Framework resolves ambiguity in representational geometry construction

Applications

Sensory Neuroscience: Understanding how sensory systems encode information across scales
Neural Coding: Characterizing population codes in cortex with geometric tools
Brain-Computer Interfaces: Optimizing decoding algorithms
Computational Neuroscience: Modeling neural population dynamics
AI Interpretability: Analyzing representations in artificial neural networks

Methodology Steps

Data Collection: Record neural population responses to stimulus set
Response Statistics: Characterize neural response variability (covariance structure)
Diffusion Model Estimation: Learn metric tensor via diffusion-based approach
Multi-Scale Analysis: Analyze geometry at multiple population scales
Information Quantification: Map expanded/contracted directions to mutual information
Eigenvector Analysis: Identify most informative stimulus variations

Related Concepts

Fisher information metric
Neural representational similarity analysis (RSA)
Information bottleneck theory
Population coding efficiency
Sensory discrimination thresholds
Amari-Nagaoka information geometry

Implementation Notes

Requires neural population recordings (electrophysiology, calcium imaging, or model simulations)
Diffusion model estimation is key to scalability
Can be applied to both biological and artificial neural networks
Connects to existing neuroscience analysis toolkits

References

Azeglio, S., Laquitaine, S., Ferrari, U., & Chalk, M. (2026). A multi-scale information geometry reveals the structure of mutual information in neural populations. arXiv:2605.06304v1

Activation Keywords

multi-scale information geometry
neural population analysis
representational geometry
information geometry neuroscience
neural coding analysis
mutual information neural
Riemannian neural geometry
diffusion models neuroscience
Fisher information metric neural

name	multi-scale-info-geometry-neural
description	Multi-scale information geometry framework revealing the structure of mutual information in neural populations. A unique Riemannian representational geometry emerges from coarse-graining, extending Fisher information metric to capture encoding structure from fine to coarse stimulus distinctions. Use when researching neural population coding, information geometry, Fisher information in neuroscience, or neural representational geometry. Based on arXiv:2605.06304.
arxiv_id	2605.06304
published	2026-05-07T00:00:00.000Z
category	neuroscience
tags	["neuroscience","information-geometry","neural-coding","multi-scale","mutual-information","fisher-information","riemannian-geometry","representational-geometry","neural-population-coding"]
related_skills	[]

name	multi-scale-info-geometry-neural
description	Multi-scale information geometry framework revealing the structure of mutual information in neural populations. A unique Riemannian representational geometry emerges from coarse-graining, extending Fisher information metric to capture encoding structure from fine to coarse stimulus distinctions. Use when researching neural population coding, information geometry, Fisher information in neuroscience, or neural representational geometry. Based on arXiv:2605.06304.
arxiv_id	2605.06304
published	2026-05-07T00:00:00.000Z
category	neuroscience
tags	["neuroscience","information-geometry","neural-coding","multi-scale","mutual-information","fisher-information","riemannian-geometry","representational-geometry","neural-population-coding"]
related_skills	[]