Extracting Slow Subspaces from Natural Videos Leads to Complex Cells

Authors:
Christoph Kayser;Wolfgang Einhäuser;Olaf Dümmer;Peter König;Konrad P. Körding
Affiliations:
-;-;-;-;-
Venue:
ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Year:
2001

Citing 3
Cited 8

Connectionist learning procedures

Artificial Intelligence
Learning invariance from transformation sequences

Neural Computation
Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces

Neural Computation

Receptive Fields Similar to Simple Cells Maximize Temporal Coherence in Natural Video

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Learning Multiple Feature Representations from Natural Image Sequences

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Applying Slow Feature Analysis to Image Sequences Yields a Rich Repertoire of Complex Cell Properties

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
An Adaptive Hierarchical Model of the Ventral Visual Pathway Implemented on a Mobile Robot

BMCV '02 Proceedings of the Second International Workshop on Biologically Motivated Computer Vision
Invariant Object Recognition with Slow Feature Analysis

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Nonlinear dimensionality reduction using a temporal coherence principle

Information Sciences: an International Journal
Invariant object recognition and pose estimation with slow feature analysis

Neural Computation
Learning invariance from natural images inspired by observations in the primary visual cortex

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Natural videos obtained from a camera mounted on a cat's head are used as stimuli for a network of subspace energy detectors. The network is trained by gradient ascent on an objective function defined by the squared temporal derivatives of the cells' outputs. The resulting receptive fields are invariant to both contrast polarity and translation and thus resemble complex type receptive fields.