Extracting Slow Subspaces from Natural Videos Leads to Complex Cells

  • Christoph Kayser
  • Wolfgang Einhäuser
  • Olaf Dümmer
  • Peter König
  • Konrad Körding
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2130)

Abstract

Natural videos obtained from a camera mounted on a catś 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.

Keywords

Computational Neuroscience Learning Temporal Smothness 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Betsch, B.Y., Körding, K.P., Einhäuser, W., König, P. What cats see-statistics of natural images. SubmitedGoogle Scholar
  2. Földiak, P. (1991). Learning Invariance from Transformation Sequences. Neural Computation, 3(2):194–200.CrossRefGoogle Scholar
  3. Fukushima, K. (1988). Neocognitron: A hierarchical neural network capable of visual pattern recognition. Neural Networks, 1, 119–130.CrossRefGoogle Scholar
  4. Grossberg, S. (1976) A neuronal model of attention, reinforcement and discrimination learning. International Review of Neurobiology, 18:263–327.CrossRefGoogle Scholar
  5. Hebb, D.O. (1949) The Organization of Behaviour: A Neurophysiological Theory. Wiley Hinton, G.E. (1989) Connectionist Learning Prcedures. Artificial Intelligence, 40:185–234.Google Scholar
  6. Hyvarinen, A., and Hoyer, P.O. (2000). Emergence of phase and shift invariant features by decomposition of natural images into independent feature subspaces. Neural Comput., 12, 1705–20.CrossRefGoogle Scholar
  7. Kohonen, T. (1996). Emergence of Invariant-Feature Detectors in the Adaptive-Subspace SOM. Biological Cybernetics, 75(4):281–291.MATHCrossRefGoogle Scholar
  8. Körding, K.P., König, P. Learning with two sites of synaptic integration. Network: Computation in neural systems, 11:1–15.Google Scholar
  9. Oja, E. (1982) A simplified neuron model as a principal component analyzer. J. of Mathematical Biology, 15:267–273.MATHCrossRefMathSciNetGoogle Scholar
  10. Riesenhuber, M., Poggio, T. (1999) Hierachical model of object recognition in cortex. Nature Neuroscience, 2(11):1019–1025CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Christoph Kayser
    • 1
  • Wolfgang Einhäuser
    • 1
  • Olaf Dümmer
    • 1
  • Peter König
    • 1
  • Konrad Körding
    • 1
  1. 1.Institute of NeuroinformaticsETH / University ZürichZürichSwitzerland

Personalised recommendations