Abstract
We study an artificial neural network that learns the invariance properties of objects from data. We start with a bag-of-features encoding of a specific object and repeatedly show the object in different transformations. The network then learns unsupervised from the data what the possible transformations are and what feature arrangements are typical for the object shown. The information about transformations and feature arrangements is hereby represented by a lateral network of excitatory connections among units that control the information exchange between an input and a down-stream neural layer. We build up on earlier work in this direction that kept a close relation to novel anatomical and physiological data on the cortical architecture and on its information processing and learning. At the same time we show, based on a new synaptic plasticity rules, that learning results in a strong increase of object finding rates in both artificial and more realistic experiments.
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
Mel, B.W.: Combining color, shape, and texture histogramming in a neurally-inspired approach to visual object recognition. Neural. Comp. 9, 777–804 (1997)
Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nature Neuroscience 211(11), 1019–1025 (1999)
Hinton, G., Osindero, S., Teh, Y.: A fast learning algorithm for deep belief nets. Neural Computation 18, 1527–1554 (2006)
Friston, K.: Hierarchical models in the brain. PLoS Computational Biology 4(11), e10000211 (2008)
Olshausen, B.A., Anderson, C.H., Essen, D.C.V.: A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information. Journal of Neuroscience 13(11), 4700–4719 (1993)
Wiskott, L., von der Malsburg, C.: Face recognition by dynamic link matching. In: Sirosh, J., Miikkulainen, R., Choe, Y. (eds.) Lateral Interactions in the Cortex: Structure and Function (1995), ISBN 0-9647060-0-8
Lücke, J., Keck, C., von der Malsburg, C.: Rapid convergence to feature layer correspondences. Neural Computation 20(10), 2441–2463 (2008)
Wolfrum, P., Wolff, C., Lücke, J., von der Malsburg, C.: A recurrent dynamic model for correspondence-based face recognition. Journal of Vision 8(7), 1–18 (2008)
Lücke, J.: Receptive field self-organization in a model of the fine-structure in V1 cortical columns. Neural Computation 21(10), 2805–2845 (2009)
Hinton, G.E.: A Parallel Computation that Assigns Canonical Object-Based Frames of Reference. In: Proc. IJCAI, pp. 683–685 (1981)
Lücke, J., Bouecke, J.D.: Dynamics of cortical columns – self-organization of receptive fields. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3696, pp. 31–37. Springer, Heidelberg (2005)
Lücke, J., von der Malsburg, C.: Rapid Processing and Unsupervised Learning in a Model of the Cortical Macrocolumn. Neural Computation 16, 501–533 (2004)
Yoshimura, Y., Dantzker, J.L.M., Callaway, E.M.: Excitatory cortical neurons form fine-scale functional networks. Nature 433, 868–873 (2005)
Yuille, A.L., Geiger, D.: Winner-take-all networks. In: Arbib, M.A. (ed.) The handbook of brain theory and neural networks, pp. 1228–1231. MIT Press, Cambridge (2003)
Lücke, J., Sahani, M.: Maximal Causes for Non-linear Component Extraction. Journal of Machine Learning Research 9, 1227–1267 (2008)
Ringach, D.L.: Spatial structure and symmetry of simple-cell receptive fields in macaque primary visual cortex. Journal of Neurophysiology 88, 455–463 (2002)
Zhu, J., von der Malsburg, C.: Maplets for correspondence-based object recognition. Neural Networks 17(8-9), 1311–1326 (2004)
Bouecke, J.D., Lücke, J.: Learning of neural information routing for correspondence finding. In: Alippi, C., Polycarpou, M., Panayiotou, C., Ellinas, G. (eds.) ICANN 2009. LNCS, vol. 5769, pp. 557–566. Springer, Heidelberg (2009)
Sato, Y.D., Jitsev, J., Malsburg, C.: A visual object recognition system invariant to scale and rotation. In: Kůrková, V., Neruda, R., Koutník, J. (eds.) ICANN 2008, Part I. LNCS, vol. 5163, pp. 991–1000. Springer, Heidelberg (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Keck, C., Lücke, J. (2010). Learning of Lateral Connections for Representational Invariant Recognition. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds) Artificial Neural Networks – ICANN 2010. ICANN 2010. Lecture Notes in Computer Science, vol 6354. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15825-4_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-15825-4_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15824-7
Online ISBN: 978-3-642-15825-4
eBook Packages: Computer ScienceComputer Science (R0)