Kernel-based extraction of Slow Features: Complex cells learn disparity and translation invariance from natural images

Alistair Bray 1 Dominique Martinez 2
1 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
2 CORIDA - Robust control of infinite dimensional systems and applications
IECN - Institut Élie Cartan de Nancy, LMAM - Laboratoire de Mathématiques et Applications de Metz, Inria Nancy - Grand Est
Abstract : In Slow Feature Analysis (\cite{Wiskott02}), it has been demonstrated that high-order invariant properties can be extracted by projecting inputs into a nonlinear space and computing the slowest changing features in this space; this has been proposed as a simple general model for learning nonlinear invariances in the visual system. However, this method is highly constrained by the curse of dimensionality which limits it to simple theoretical simulations. This paper demonstrates that by using a different but closely-related objective function for extracting slowly varying features (\cite{Stone95a,Stone01}), and then exploiting the kernel trick, this curse can be avoided. Using this new method we show that both the complex cell properties of translation invariance and disparity coding can be learnt simultaneously from natural images when complex cells are driven by simple cells also learnt from the image.
Type de document :
Communication dans un congrès
Neural Information Processing Systems - NIPS'02, 2002, Vancouver, Canada, 8 p, 2002
Liste complète des métadonnées

https://hal.inria.fr/inria-00100796
Contributeur : Publications Loria <>
Soumis le : mardi 26 septembre 2006 - 14:51:06
Dernière modification le : jeudi 11 janvier 2018 - 06:20:02

Identifiants

  • HAL Id : inria-00100796, version 1

Collections

Citation

Alistair Bray, Dominique Martinez. Kernel-based extraction of Slow Features: Complex cells learn disparity and translation invariance from natural images. Neural Information Processing Systems - NIPS'02, 2002, Vancouver, Canada, 8 p, 2002. 〈inria-00100796〉

Partager

Métriques

Consultations de la notice

185