Slow feature analysis yields a rich repertoire of complex cell properties

Berkes, Pietro and Wiskott, Laurenz (2003) Slow feature analysis yields a rich repertoire of complex cell properties. [Preprint]

This is the latest version of this eprint.

Full text available as:



In this study, we investigate temporal slowness as a learning principle for receptive fields using slow feature analysis, a new algorithm to determine functions that extract slowly varying signals from the input data. We find that the learned functions trained on image sequences develop many properties found also experimentally in complex cells of primary visual cortex, such as direction selectivity, non-orthogonal inhibition, end-inhibition and side-inhibition. Our results demonstrate that a single unsupervised learning principle can account for such a rich repertoire of receptive field properties.

Item Type:Preprint
Keywords:complex cells, slow feature analysis, temporal slowness, model, spatio-temporal, receptive fields
Subjects:Neuroscience > Computational Neuroscience
Computer Science > Machine Vision
ID Code:2804
Deposited By: Berkes, Pietro
Deposited On:04 Mar 2003
Last Modified:11 Mar 2011 08:55

Available Versions of this Item

References in Article

Select the SEEK icon to attempt to find the referenced article. If it does not appear to be in cogprints you will be forwarded to the paracite service. Poorly formated references will probably not work.

Bell, A. J., Sejnowski, T. J., 1997, The independent components of natural scenes are edge filters, Vision Research 37 (23), 3327-3338.

Berkes, P., Wiskott, L., 2002, Applying slow feature analysis to image sequences yields a rich repertoire of complex cell properties, In: Dorronsoro, J. R. (Ed.), Artificial Neural Networks - ICANN 2002 Proceedings. Lecture Notes in Computer Science. Springer, pp. 81-86.

De Valois, R., Yund, E., Hepler, N., 1982, The orientation and direction selectivity of cells in macaque visual cortex, Vision Res. 22 (5), 531-44.

DeAngelis, G., Freeman, R., Ohzawa, I., 1994, Length and width tuning of neurons in the cat's primary visual cortex, Journal of Neurophysiology 71 (1), 347-74.

Dobbins, A., Zucker, S. W., Cynader, M. S., October 1987, Endstopped neurons in the visual cortex as a substrate for calculating curvature, Nature 329, 438-441.

Einhäuser, W., Kayser, C., Körding, K., König, P., 2002, Learning multiple feature representation from natural image sequences, In: Dorronsoro, J. R. (Ed.), Artificial Neural Networks - ICANN 2002 Proceedings. Lecture Notes in Computer Science. Springer, pp. 21-26.

Földiák, P., 1991, Learning invariance from transformation sequences, Neural Computation 3, 194-200.

Gantmacher, 1959, Matrix Theory Vol. 1, AMS Chelsea Publishing.

Hinton, G., 1989, Connectionist learning procedures, Artificial Intelligence 40, 185-234.

Hoyer, P., Hyvärinnen, A., 2000, Independent component analysis applied to feature extraction from colour and stereo images, Network: Computation in Neural Systems 11 (3), 191-210.

Hubel, D., Wiesel, T., 1962, Receptive fields, binocular interaction and functional architecture in the cat's visual cortex, Journal of Physiology 160, 106-154.

Hurri, J., Hyvärinnen, A., 2003, Simple-cell-like receptive fields maximize temporal coherence in natural video, Neural Computation, 15(3), pp. 663-691.

Hyvärinnen, A., Hoyer, P., 2000, Emergence of phase and shift invariant features by decomposition of natural images into independent features subspaces, Neural Computation 12 (7), 1705-1720.

Kayser, C., Einhäuser, W., Dümmer, O., König, P., Körding, K., 2001, Extracting slow subspaces from natural videos leads to complex cells, In: Artificial Neural Networks - ICANN 2001 Proceedings. Springer, pp. 1075-1080.

Mitchison, G., 1991, Removing time variation with the anti-Hebbian differential synapse, Neural Computation 3, 312-320.

Olshausen, B., 2002, Sparse codes and spikes. In: Rao, R. P. N., Olshausen, B. A., Lewicki, M. S. (Eds.), Probabilistic Models of the Brain: Perception and Neural Function, MIT Press.

Olshausen, B., Field, D., Jun 1996, Emergence of simple-cell receptive field properties by learning a sparse code for natural images, Nature 381 (6583), 607-609.

Schiller, P., Finlay, B., Volman, S., 1976, Quantitative studies of single-cell properties in monkey striate cortex. I. Spatiotemporal organization of receptive fields, J. Neurophysiol. 39 (6), 1288-1319.

Shevelev, I. A., 1998, Second-order features extraction in the cat visual cortex: selective and invariant sensitivity of neurons to the shape and orientation of crosses and corners, BioSystems 48, 195-204.

Sillito, A., 1975, The contribution of inhibitory mechanisms to the receptive field properties of neurons in the striate cortex of the cat, J. Physiol. 250, 305-329.

Stone, J. V., 1996, Learning perceptually salient visual parameters using spatiotemporal smoothness constraints, Neural Computation 8, 1463-1492.

Stone, J. V., 2001, Blind source separation using temporal predictability, Neural Computation 13, 1559-1574.

Szatmáry, B., Lörincz, A., 2001, Independent component analysis of temporal sequences subject to constraints by lateral geniculate nucleus inputs yields all three major cell types of the primary visual cortex, Journal of Computational Neuroscience 11, 241-248.

van Hateren, J., van der Schaaf, A., 1998, Independent component filters of natural images compared with simple cells in primary visual cortex, Proc. R. Soc. Lond. B 265, 359-366.

Versavel, M., Orban, G. A., Lagae, L., 1990, Responses of visual cortical neurons to curved stimuli and chevrons, Vision Res. 30 (2), 235-248.

Wiskott, L., 1998, Learning invariance manifolds, In: Niklasson, L., Bodén, M., Ziemke, T. (Eds.), Proc. Intl. Conf. on Artificial Neural Networks, ICANN 98, Skövde. Perspectives in Neural Computing. Springer, pp. 555-560.

Wiskott, L., Sejnowski, T., 2002, Slow feature analysis: Unsupervised learning of invariances, Neural Computation 14 (4), 715-770.


Repository Staff Only: item control page