Abstract
We address the technical challenges involved in combining key features from several theories of the visual cortex in a single coherent model. The resulting model is a hierarchical Bayesian network factored into modular component networks embedding variable-order Markov models. Each component network has an associated receptive field corresponding to components residing in the level directly below it in the hierarchy. The variable-order Markov models account for features that are invariant to naturally occurring transformations in their inputs. These invariant features give rise to increasingly stable, persistent representations as we ascend the hierarchy. The receptive fields of proximate components on the same level overlap to restore selectivity that might otherwise be lost to invariance.
Similar content being viewed by others
References
Adelson, E., Movshon, J.: Phenomenal coherence of moving visual patterns. Nature 300, 523–525 (1982)
Barto, A.G., Sutton, R.S., Anderson, C.W.: Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Trans. Syst. Man Cybernet. 13(5), 835–846 (1983)
Basye, K., Dean, T., Kirman, J., Lejter, M.: A decision-theoretic approach to planning, perception, and control. IEEE Expert 7(4), 58–65 (1992)
Bengio, Y., Frasconi, P.: An input output HMM architecture. In: e. a. Cowan, J.D. (ed.) Advances in Neural Information Processing, vol. 6. Morgan Kaufmann, San Francisco, CA (1994)
Berkes, P., Wiskott, L.: Slow feature analysis yields a rich repertoire of complex cell properties. J. Vis. 5(6), 579–602 (2005)
Bishop, C.M., Svensén, M., Williams, C.K.I.: GTM: A principled alternative to the self-organizing map. In: Mozer, M.C., Jordan, M.I., Petsche, T. (eds.) Advances in Neural Information Processing Systems, vol. 9, pp. 354–360. MIT, Cambridge, MA (1997)
Braitenberg, V., Schuz, A.: Cortex: Statistics and Geometry of Neuronal Connections. Springer, Berlin Heidelberg New York (1991)
Bray, A., Martinez, D.: Kernel-based extraction of slow features: complex cells learn disparity and translation invariance from natural images. In: Advances in Neural Information Processing Systems, vol. 14. MIT, Cambridge, MA (2002)
Burns, G., Daoud, R., Vaigl, J.: LAM: An open cluster environment for MPI. In: Proceedings of Supercomputing Symposium, pp. 379–386 (1994)
Cowell, R.G., Dawid, A.P., Lauritzen, S.L., Spiegelhalter, D.J.: Probabilistic networks and expert systems. Springer, Berlin Heidelberg New York (1999)
Dean, T.: A computational model of the cerebral cortex. In: Proceedings of AAAI-05, pp. 938–943. MIT, Cambridge, MA (2005)
Dean, T.: Scalable inference in hierarchical generative models. In: Proceedings of the Ninth International Symposium on Artificial Intelligence and Mathematics, (2006)
Dean, T., Kanazawa, K.: A model for reasoning about persistence and causation. Comput. Intel. J. 5(3), 142–150 (1989)
Elidan, G., McGraw, I., Koller, D.: Residual belief propagation: informed scheduling for asynchronous message passing. In: Proceedings of the Twenty-second Conference on Uncertainty in AI (UAI), Boston, MA, July 2006
Eskin, E., Grundy, W.N., Singer, Y.: Protein family classification using sparse markov transducers. In: Proceedings of the Eighth International Conference on Intelligent Systems for Molecular Biology, pp. 134–145 (2000)
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: Proceedings of CVPR-05 Workshop on Generative-Model Based Vision (2004)
Fei-Fei, L., Perona, P.: A Bayesian hierarchical model for learning natural scene categories. In: Proceedings of CVPR (2005)
Fine, S., Singer, Y., Tishby, N.: The hierarchical hidden Markov model: analysis and applications. Mach. Learn. 32(1), 41–62 (1998)
Földiák, P.: Learning invariance from transformation sequences. Neural Comput. 3, 194–200 (1991)
Friedman, N.: The Bayesian structural EM algorithm. In: Proceedings of the Conference on Uncertainty in Artificial Intelligence, pp. 129–138 (1998)
Friedman, N., Geiger, D., Goldszmidt, M.: Bayesian network classifiers. Mach. Learn. 29(2-3), 131–163 (1997)
Fukushima, K.: Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 93–202 (1980)
George, D., Hawkins, J.: A hierarchical Bayesian model of invariant pattern recognition in the visual cortex. In: Proceedings of the International Joint Conference on Neural Networks, vol. 3, pp. 1812–1817. IEEE (2005)
Hawkins, J., Blakeslee, S.: On Intelligence. Henry Holt and Company, New York, (2004)
Hawkins, J., George, D.: Hierarchical temporal memory: concepts, theory and terminology, (2006)
Heckerman, D.: A tutorial on learning Bayesian networks. Tech. Rep. MSR-95-06, Microsoft Research (1995)
Hinton, G.: Product of experts. In: Proceedings of International Conference on Neural Networks. vol. 1, pp. 1–6 (1999)
Hinton, G., Sejnowski, T.: Learning and relearning in Boltzmann machines. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Volume I: Foundations, pp. 282–317. MIT, Cambridge MA (1986)
Hinton, G.E., Osindero, S., Teh, Y.-W.: A fast learning algorithm for deep belief nets. Neural Comput. (2006)
Huang, C., Darwiche, A.: Inference in belief networks: a procedural guide. Int. J. Approx. Reason. 15(3), 225–263 (1996)
Hubel, D.H.: Eye, Brain and Vision (Scientific American Library, Number 22). Freeman, San Francisco, CA (1995)
Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. J. Physiol. 160, 106–154 (1962)
Jackendoff, R.: Foundations of Language: Brain, Meaning, Grammar, Evolution. Oxford University Press, Oxford, UK (2002)
Jensen, F.: Bayesian graphical models. Wiley, New York, NY (2000)
Jordan, M. (ed.): Learning in Graphical Models. MIT, Cambridge, MA (1998)
Kabán, A., Girolami, M.: A dynamic probabilistic model to visualise topic evolution in text streams. Journal of Intelligent Information System 18(2-3), 107–125 (2003)
Kearns, M., Valiant, L.G.: Cryptographic limitations on learning boolean functions and finite automata. In: Proceedings of the Twenty First Annual ACM Symposium on Theoretical Computing, pp. 433–444 (1989)
Kubovy, M., Gepshtein, S.: Perceptual grouping in space and in space-time: an exercise in phenomenological psychophysics. In: Behrmann, M., Kimchi, R., Olson, C.R. (eds.) Perceptual Organization in Vision: Behavioral and Neural Perspectives, pp. 45–85. Lawrence Erlbaum, Mahwah, NJ, (2003)
Kulikowski, J.J., Bishop, P.O.: Fourier analysis and spatial representation in the visual cortex. Experientia 37, 160–163 (1981)
LeCun, Y., Huang, F.-J., Bottou, L.: Learning methods for generic object recognition with invariance to pose and lighting. In: Proceedings of IEEE Computer Vision and Pattern Recognition, IEEE Press (2004)
LeCun, Y., Matan, O., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D., Baird, H.S.: Handwritten zip code recognition with multilayer networks. In: Proceedings of the International Conference on Pattern Recognition. IAPR, Ed., vol. II, pp. 35–40. IEEE Press (1990)
Lee, T.S., Mumford, D.: Hierarchical Bayesian inference in the visual cortex. J. Opt. Soc. Am. 2(7), 1434–1448 (July 2003)
Mayraz, G., Hinton, G.: Recognizing handwritten digits using hierarchical products of experts. IEEE Trans. Pattern Anal. Mach. Intel. 24, 189–197 (2002)
McClelland, J., Rumelhart, D.: An interactive activation model of context effects in letter perception: I. An account of basic findings. Psychol. Rev. 88, 375–407 (1981)
Murphy, G.L.: The Big Book of Concepts. MIT, Cambridge, MA (2002)
Murphy, K.: The Bayes Net Toolbox for Matlab. Comput. Sci. Stat. 33 (2001)
Murphy, K., Weiss, Y., Jordan, M.: Loopy-belief propagation for approximate inference: an empirical study. In: Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence, pp. 467–475. Morgan Kaufmann, San Mateo, CA (2000)
Murphy, K.P.: Dynamic Bayesian Networks: Representation, Inference and Learning. Ph.D. thesis, University of California, Berkeley, Computer Science Division (2002)
Murray, S.O., Olshausen, B.A., Woods, D.L.: Processing shape, motion and three-dimensional shape-from-motion in the human cortex. Cerebral Cortex 13(5), 508–516 (2003)
Ng, A., Jordan, M., Weiss, Y.: On spectral clustering: analysis and an algorithm. In: Advances in Neural Information Processing Systems, vol. 14. MIT, Cambridge, MA (2002)
Olshausen, B.A., Anderson, A., Van Essen, D.C.: A neurobiological model of visual attention and pattern recognition based on dynamic routing of information. J. Neurosci. 13(11), 4700–4719 (1993)
Olshausen, B.A., Field, D.J.: How close are we to understanding V1? Neural Comput. 17, 1665–1699 (2005)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco, CA (1988)
Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. In: Proceedings of IEEE, vol. 77(2), pp. 257–286 (1989)
Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nat. Neurosci. 2(11), 1019–1025 (November 1999)
Rivest, R.L., Sloan, R.: A formal model of hierarchical concept learning. Inf. Comput. 114(1), 88–114 (1994)
Ron, D., Singer, Y., Tishby, N.: The power of amnesia: learning probabilistic automata with variable memory length. Mach. Learn. 25(2,3), 117–149 (1996)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Rumelhart, D.E., McClelland, J.L. (eds.) Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Volume 1: Foundations. MIT, Cambridge, MA (1986)
Sage, K.H., Buxton, H.: Joint spatial and temporal structure learning for task based control. In: International Conference on Pattern Recognition (ICPR), vol. 2, pp. 48–51 (2004)
Ullman, S.: The Interpretation of Visual Motion. MIT, Cambridge, MA, USA, (1979)
Ullman, S., Soloviev, S.: Computation of pattern invariance in brain-like structures. Neural Netw. 12, 1021–1036 (1999)
Valiant, L.G.: A theory of the learnable. Commun. ACM 27, 1134–1142 (1984)
Verbeek, J., Vlassis, N., Kröse, B.: Efficient greedy learning of Gaussian mixtures. Neural Comput. 15(2), 469–485 (2003)
Wertheimer, M.: Untersuchungen zur lehre von der gestalt, II (Investigations of the principles of gestalt, II). Psychol. Forsch. 4, 301–350 (1923)
Wiskott, L., Sejnowski, T.: Slow feature analysis: unsupervised learning of invariances. Neural Comput. 14(4), 715–770 (2002)
Yedidia, J.S., Freeman, W.T., Weiss, Y.: Understanding belief propagation and its generalizations. In: Lakemeyer, G., Nebel, B. (eds.) Exploring Artificial Intelligence in the New Millennium, pp. 239–269. Morgan Kaufmann, San Francisco, CA (2003)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Dean, T. Learning invariant features using inertial priors. Ann Math Artif Intell 47, 223–250 (2006). https://doi.org/10.1007/s10472-006-9039-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10472-006-9039-9