Abstract
Recently, statistical models of natural images have shown emergence of several properties of the visual cortex. Most models have considered the non-Gaussian properties of static image patches, leading to sparse coding or independent component analysis. Here we consider the basic statistical time dependencies of image sequences. We show that simple cell type receptive fields emerge when temporal response strength correlation is maximized for natural image sequences. Thus, temporal response strength correlation, which is a nonlinear measure of temporal coherence, provides an alternative to sparseness in modeling simple cell receptive field properties. Our results also suggest an interpretation of simple cells in terms of invariant coding principles that have previously been used to explain complex cell receptive fields.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Palmer, S.E.: Vision Science-Photons to Phenomenology. The MIT Press (1999)
Olshausen, B.A., Field, D.: Emergence of simple-Cell receptive field properties by learning a sparse code for natural images. Nature 381 (1996) 607–609
Bell, A., Sejnowski, T.J.: The independent components of natural scenes are edge filters. Vision Research 37 (1997) 3327–3338
van Hateren, J.H., van der Schaaf, A.: Independent component filters of natural images compared with simple cells in primary visual cortex. Proceedings of the Royal Society of London B 265 (1998) 359–366
Hyvärinen, A., Karhunen, J., Oje, E.: Independent Component Analysis. John Wiley & Sons (2001)
Földiak, P.: Learning invariance from transformation sequences. Neural Computation 3 (1991) 194–200
Kayser, C., Einhäuser, W., Dümmer, O., König, P., Körding, K.: Extracting slow subspaces from natural Videos leads to complex cells. In Dorffner, G., Bischof, H., Hornik, K., eds.: Artificial Neural Networks-ICANN 2001, Springer (2001) 1075–1080
Wiskott, L., Sejnowski, T.J.: Slow feature analysis: Unsupervised learning of invariances. Neural Computation 14 (2002) 715–770
Stone, J.: Learning visual Parameters using spatiotemporal smoothness constraints. Neural Computation 8 (1996) 1463–1492
Hurri, J., Hyvärinen, A.: Simple-cell-like receptive fields maximize temporal coherence in natural Video. Submitted manuscript, electronie version available at http://www.cis.hut.fi/jarmo/publications/ (2001)
van Hateren, J.H., Ruderman, D.L.: Independent component analysis of natural image sequences yields spatio-temporal filters similar to simple cells in primary visual cortex. Proceedings of the Royal Society of London B 265 (1998) 2315–2320
Dong, D.W., Atick, J.: Temporal decorrelation: a theory of lagged and nonlagged responses in the lateral geniculate nucleus. Network: Computation in Neural Systems 6 (1995) 159–178
Kohonen, T., Kaski, S., Lappalainen, H.: Self-organized formation of various invariant-feature filters in the adaptive-subspace SOM. Neural Computation 9 (1997) 1321–1344
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hurri, J., Hyvärinen, A. (2002). Receptive Fields Similar to Simple Cells Maximize Temporal Coherence in Natural Video. In: Dorronsoro, J.R. (eds) Artificial Neural Networks — ICANN 2002. ICANN 2002. Lecture Notes in Computer Science, vol 2415. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46084-5_6
Download citation
DOI: https://doi.org/10.1007/3-540-46084-5_6
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44074-1
Online ISBN: 978-3-540-46084-8
eBook Packages: Springer Book Archive