Abstract
Regarding biological visual classification, recent series of experiments have enlighten the fact that data classification can be realized in the human visual cortex with latencies of about 100–150 ms, which, considering the visual pathways latencies, is only compatible with a very specific processing architecture, described by models from Thorpe et al.
Surprisingly enough, this experimental evidence is in coherence with algorithms derived from the statistical learning theory. More precisely, there is a double link: on one hand, the so-called Vapnik theory offers tools to evaluate and analyze the biological model performances and on the other hand, this model is an interesting front-end for algorithms derived from the Vapnik theory.
The present contribution develops this idea, introducing a model derived from the statistical learning theory and using the biological model of Thorpe et al. We experiment its performances using a restrained sign language recognition experiment.
This paper intends to be read by biologist as well as statistician, as a consequence basic material in both fields have been reviewed.
Similar content being viewed by others
References
Bajcsy R, Solina F (1987) Three dimensional object representa-tion revisited. In: Proceedings of the 1st International Conference on Computer Vision. London, England, IEEE Computer Society Press.
Bartlett P, Shawe-Taylor J (1999) Generalization performance of sup-port vector machines and other pattern classifiers. In: B Schölkopf, C Burges, A Smola, eds. Advances in Kernel Methods, Support Vector Learning. The MIT Press, Cambridge, Chapt. 4, pp. 43–54.
Baum E, Haussler D (1989) What size net gives valid generalization. Neural Comput. 1: 151–160.
Benedetti R, Risler J-J (1990) Real Algebraic and Semi-Algebraic Sets. Hermann, Paris.
Bugmann G (1997) Biologically plausible neural computation. Biosystems 40: 11–19.
Bullier J (2001) Integrated model of visual processing. Brain Res. Reviews 36: 96–107.
Burnod Y(1993) An Adaptive Neural Network: The Cerebral Cortex, 2nd edition. Masson, Paris.
Carr CE (1993) Processing of temporal information in the brain. Annu. Rev. Neurosci. 16: 223–244.
Chang C-C, Lin C-J (2001) Training nu-support vector classi-fiers: Theory and algorithms. Neural Comput. 13(9): 2119–214.
Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans. on Information Theory 13(1).
Delorme A, Gautrais J, Van Rullen R, Thorpe SJ (1999) SpikeNET: A simulator for modeling large networks of integrate and fire neurons. Neurocomput. 26: 989–996.
Delorme A, Richard G, Fabre-Thorpe M(2000) Rapid categorisation of natural scenes is colour blind: A study in monkeys and humans. Vision Research 40(16): 2187–2200.
Delorme A, Thorpe S (2001) Face processing using one spike per neuron: Resistance to image degradation. Neural Networks 14: 795–804.
Duda RO, Hart PE, Stork DG (2000) Pattern Classification, 2nd edition. Wiley Interscience.
Durbin R, Miall C, Mitchinson G, eds. (1989) The Computing Neuron. Addison-Wesley.
Figueiredo MAT, Jain AK (2001) Bayesian learning of sparse classifiers. In: Computer Vision and Pattern Recognition.
Freedman DJ, Riesenhuber M, Poggio T, Miller EK (2002) Cate-gorical representation of visual stimuli in the primate prefrontal cortex. Science 291(5502): 312–316.
Friess T, Cristianini N, Campbell C (1998) The kernel adatron al-gorithm: A fast and simple learning procedure for support vec-tor machine. In: Proc. 15th International Conference on Machine Learning. Morgan Kaufman.
Gaspard F, Viéville T (2000) Non linear minimization and visual localization of a plane. In: The 6th International Conference on Information Systems, Analysis and Synthesis, Vol. VIII, pp. 366–371.
Gautrais J, Thorpe S (1998) Rate coding vs temporal order coding: A theorical approach. Biosystems 48: 57–65.
Gisiger T, Dehaene S, Changeux JP (2000) Computational models of association cortex. Curr. Opin. Neurobiol. 10: 250–259.
Guermeur Y (2002a) Combining discriminant models with new multi-class SVMs. Pattern Analysis and Applications 5(2): 168–179.
Guermeur Y(2002b) Asimple unifying theory of multi-class support vector machines. Technical Report 4669, INRIA.
Gutierrez-Galvez A, Gutierrez-Osuna R (2003) Pattern completion through phase coding in population neurodynamics. Neural Networks 16: 649–656.
Hubel D (1994) L'oeil, le Cerveau et la Vision: Les étapes cérébrales du traitement visuel, L'univers des sciences. Pour la science.
Huerta R, Nowotn T, García-Sanchez M, Abarbanel HDI, Rabinovich MI (2004) Learning classification in the olfactory system of insects. In preparation.
Koiran P, Sontag E (1996) Neural networks with quadratic VC dimension.
Advances in Neural Information Processing System 8: 197–203.
Krauth W, Mezard M (1987) Learning algorithms with optimal stability in neural networks. J. Phis. 20}: 745–752.
Marr D (1982) Vision. W.H. Freeman and Co.
Mezard M, Nadal J (1989) Learning in feed forward layered net-works: The tiling algorithm. J. Phys. 22: 2191–2204.
Novak L, Bullier J (1997) The Timing of Information Transfer in the Visual System, Vol. 12 of Cerebral Cortex, Chap. 5, pp. 205–241. Plenum Press, New York.
Rolls ET, Treves A (1998) Neural Networks and Brain Function. Oxford University Press.
Shawe-Taylor J, Bartlett P, Williamson R, Anthony M (1998) Structural risk minimization over data-dependent hierarchies. IEEE Trans. on Information Theory 44(5).
Soo-Young L, Dong-Gyu J (1996) Merging back-propagation and Hebbian learning rules for robust classifications. Neural Networks 9(7): 1213–1222.
Theodoridis S, Koutroumbas K (1999) Pattern Recognition. Academic Press.
Thorpe S (2002) Ultra-rapid scene categorization with a wave of spikes. In: Biologically Motivated Computer Vision, Vol. 2525 of Lecture Notes in Computer Science. Springer-Verlag Heidelberg, pp. 1–15.
Thorpe S, Delorme A, Van Rullen R (2001) Spike based strategies for rapid processing. Neural Networks 14: 715–726.
Thorpe S, Fabre-Thorpe M (2001) Seeking categories in the brain. Science 291: 260–263.
Thorpe S, Fize D, Marlot C (1996) Speed of processing in the human visual system. Nature 381: 520–522.
van Tonder GJ, Ejima Y (2000) Bottom-up clues in target finding: Why a Dalmatian may be mistaken for an elephant. Perception 29(2): 149–157.
Vapnik V(1995) The Nature of Statistical Learning Theory. Springer-Verlag.
Vapnik V (1998) Statistical Learning Theory. John Wiley.
Vieville T (2000) Using markers to compensate displacements in MRI volume sequences. Technical Report 4054, INRIA.
Vieville T, Lingrand D, Gaspard F (2001) Implementing a multi-model estimation method. The International Journal of Computer Vision 44(1).
Wilson R, Keil F (1999) The MIT Encyclopedia of the Cognitive Sciences. MIT Press, Cambridge, MA.
Yu AJ, Giese M, Poggio T (2003) Biophysiologically plausi-ble implementations of maximum operation. Neural Comput. 14(12).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Viéville, T., Crahay, S. Using an Hebbian Learning Rule for Multi-Class SVM Classifiers. J Comput Neurosci 17, 271–287 (2004). https://doi.org/10.1023/B:JCNS.0000044873.20850.9c
Issue Date:
DOI: https://doi.org/10.1023/B:JCNS.0000044873.20850.9c