Learning Invariance Manifolds of Visual Sensory Neurons

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A10492448" target="_blank" >RIV/00216208:11320/22:10492448 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Learning Invariance Manifolds of Visual Sensory Neurons

Popis výsledku v původním jazyce

Robust object recognition is thought to rely on neural mechanisms that are selective to complex stimulus features while being invariant to others (e.g., spatial location or orientation). To better understand biological vision, it is thus crucial to characterize which features neurons in different visual areas are selective or invariant to. In the past, invariances have commonly been identified by presenting carefully selected hypothesis-driven stimuli which rely on the intuition of the researcher. One example is the discovery of phase invariance in V1 complex cells. However, to identify novel invariances, a data-driven approach is more desirable. Here, we present a method that, combined with a predictive model of neural responses, learns a manifold in the stimulus space along which a target neuron&apos;s response is invariant. Our approach is fully data-driven, allowing the discovery of novel neural invariances, and enables scientists to generate and experiment with novel stimuli along the invariance manifold. We test our method on Gabor-based neuron models as well as on a neural network fitted on macaque V1 responses and show that 1) it successfully identifies neural invariances, and 2) disentangles invariant directions in the stimulus space

Název v anglickém jazyce

Learning Invariance Manifolds of Visual Sensory Neurons

Popis výsledku anglicky

Robust object recognition is thought to rely on neural mechanisms that are selective to complex stimulus features while being invariant to others (e.g., spatial location or orientation). To better understand biological vision, it is thus crucial to characterize which features neurons in different visual areas are selective or invariant to. In the past, invariances have commonly been identified by presenting carefully selected hypothesis-driven stimuli which rely on the intuition of the researcher. One example is the discovery of phase invariance in V1 complex cells. However, to identify novel invariances, a data-driven approach is more desirable. Here, we present a method that, combined with a predictive model of neural responses, learns a manifold in the stimulus space along which a target neuron&apos;s response is invariant. Our approach is fully data-driven, allowing the discovery of novel neural invariances, and enables scientists to generate and experiment with novel stimuli along the invariance manifold. We test our method on Gabor-based neuron models as well as on a neural network fitted on macaque V1 responses and show that 1) it successfully identifies neural invariances, and 2) disentangles invariant directions in the stimulus space

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

30103 - Neurosciences (including psychophysiology)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

NEURIPS WORKSHOP ON SYMMETRY AND GEOMETRY IN NEURAL REPRESENTATIONS, VOL 197

ISBN

—

ISSN

2640-3498

e-ISSN

—

Počet stran výsledku

26

Strana od-do

301-326

Název nakladatele

JMLR-JOURNAL MACHINE LEARNING RESEARCH

Místo vydání

SAN DIEGO

Místo konání akce

New Orleans

Datum konání akce

16. 12. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001227269600017