Abstract
Visual recognition faces the difficult problem of recognizing objects despite the multitude of their appearances. Ample neuroscientific evidence shows that the cortex uses a topographic code to represent visual stimuli. We therefore develop a bilinear probabilistic model that learns transformations to build an invariant topographic code in an unsupervised way. Simulations for the simple over-complete linear case yield V1 like Gabor receptive fields that are arranged in orientation, frequency and position maps. For the computationally more powerful case of two control units, we show that an application to natural inputs placed at different positions and with a consistent relative transformation (e.g. rotation), leads to an invariant topographic output representation and hence a relative implementation of the transformation in the control units, i.e. the Gabor receptive fields are transformed accordingly.
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
Willshaw, D.J., von der Malsburg, C.: How patterned neural connections can be set up by self-organization. Proc. R. Soc. Lond. B. Biol. Sci. 194(1117), 431–445 (1976)
Fukushima, K.: Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 193–202 (1980)
Wolfrum, P., Wolff, C., Lücke, J., von der Malsburg, C.: A recurrent dynamic model for correspondence-based face recognition. J. Vis. 8(7), 34.1–34.18 (2008)
Tenenbaum, J.B., Freeman, W.T.: Separating style and content with bilinear models. Neural Computation 12(6), 1247–1283 (2000)
Hyvärinen, A., Hoyer, P.O., Inki, M.: Topographic independent component analysis. Neural Comput. 13(7), 1527–1558 (2001)
Wiskott, L., Sejnowski, T.J.: Slow feature analysis: unsupervised learning of invariances. Neural Computation 14(4), 715–770 (2002)
Turner, R., Sahani, M.: A maximum-likelihood interpretation for slow feature analysis. Neural Comput. 19(4), 1022–1038 (2007)
Olshausen, B.A., Field, D.J.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381(6583), 607–609 (1996)
van Hateren, J.H., van der Schaaf, A.: Independent component filters of natural images compared with simple cells in primary visual cortex. Proc. Biol. Sci. 265(1394), 359–366 (1998)
Hopf, J.M., Boehler, C.N., Luck, S.J., Tsotsos, J.K., Heinze, H.J., Schoenfeld, M.A.: Direct neurophysiological evidence for spatial suppression surrounding the focus of attention in vision. Proc. Natl. Acad. Sci. USA 103(4), 1053–1058 (2006)
Berkes, P., Turner, R.E., Sahani, M.: A structured model of video reproduces primary visual cortical organisation. PLoS Comput. Biol. 5(9), e1000495 (Sep 2009)
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
Bergmann, U., von der Malsburg, C. (2010). A Bilinear Model for Consistent Topographic Representations. 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_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-15825-4_8
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)