Learning Invariance Manifolds of Visual Sensory Neurons

Result code in 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>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Learning Invariance Manifolds of Visual Sensory Neurons
Original language description
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'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
Czech name
—
Czech description
—

Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
NEURIPS WORKSHOP ON SYMMETRY AND GEOMETRY IN NEURAL REPRESENTATIONS, VOL 197
ISBN
—
ISSN
2640-3498
e-ISSN
—
Number of pages
26
Pages from-to
301-326
Publisher name
JMLR-JOURNAL MACHINE LEARNING RESEARCH
Place of publication
SAN DIEGO
Event location
New Orleans
Event date
Dec 16, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001227269600017

Similar results(10)