Learning Multiple Feature Representations from Natural Image Sequences

Authors:
Wolfgang Einhäuser;Christoph Kayser;Konrad P. Körding;Peter König
Affiliations:
-;-;-;-
Venue:
ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Year:
2002

Citing 4
Cited 0

Learning invariance from transformation sequences

Neural Computation
Digital Image Processing: Concepts, Algorithms, and Scientific Applications

Digital Image Processing: Concepts, Algorithms, and Scientific Applications
Extracting Slow Subspaces from Natural Videos Leads to Complex Cells

ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Hierarchical neural networks require the parallel extraction of multiple features. This raises the question how a subpopulation of cells can become specific to one feature and invariant to another, while a different subpopulation becomes invariant to the first but specific to the second feature. Using a colour image sequence recorded by a camera mounted to a cat's head, we train a population of neurons to achieve optimally stable responses. We find that colour sensitive cells emerge. Adding the additional objective of decorrelating the neurons' outputs leads a subpopulation to develop achromatic receptive fields. The colour sensitive cells tend to be non-oriented, while the achromatic cells are orientation-tuned, in accordance with physiological findings. The proposed objective thus successfully separates cells which are specific for orientation and invariant to colour from orientation invariant colour cells.