A hierarchical Bayesian model of invariant pattern recognition in the visual cortex Export

@proceedings{citeulike:1294875, abstract = {We describe a hierarchical model of invariant visual pattern recognition in the visual cortex. In this model, the knowledge of how patterns change when objects move is learned and encapsulated in terms of high probability sequences at each level of the hierarchy. Configuration of object parts is captured by the patterns of coincident high probability sequences. This knowledge is then encoded in a highly efficient Bayesian network structure. The learning algorithm uses a temporal stability criterion to discover object concepts and movement patterns. We show that the architecture and algorithms are biologically plausible. The large scale architecture of the system matches the large scale organization of the cortex and the micro-circuits derived from the local computations match the anatomical data on cortical circuits. The system exhibits invariance across a wide variety of transformations and is robust in the presence of noise. Moreover, the model also offers alternative explanations for various known cortical phenomena.}, author = {George, Dileep and Hawkins, Jeff}, citeulike-article-id = {1294875}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/IJCNN.2005.1556155}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1556155}, day = {27}, doi = {10.1109/IJCNN.2005.1556155}, journal = {Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on}, keywords = {bayesian\_network, hierarchy, pattern\_recognition, visual\_cortex}, month = {December}, pages = {1812--1817}, posted-at = {2009-11-04 14:02:59}, priority = {2}, title = {A hierarchical Bayesian model of invariant pattern recognition in the visual cortex}, url = {http://dx.doi.org/10.1109/IJCNN.2005.1556155}, volume = {3}, year = {2005} }

TY - CONF ID - citeulike:1294875 L3 - citeulike-article-id:1294875 N2 - We describe a hierarchical model of invariant visual pattern recognition in the visual cortex. In this model, the knowledge of how patterns change when objects move is learned and encapsulated in terms of high probability sequences at each level of the hierarchy. Configuration of object parts is captured by the patterns of coincident high probability sequences. This knowledge is then encoded in a highly efficient Bayesian network structure. The learning algorithm uses a temporal stability criterion to discover object concepts and movement patterns. We show that the architecture and algorithms are biologically plausible. The large scale architecture of the system matches the large scale organization of the cortex and the micro-circuits derived from the local computations match the anatomical data on cortical circuits. The system exhibits invariance across a wide variety of transformations and is robust in the presence of noise. Moreover, the model also offers alternative explanations for various known cortical phenomena. JF - Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on EP - 1817 TI - A hierarchical Bayesian model of invariant pattern recognition in the visual cortex VL - 3 SP - 1812 KW - bayesian_network KW - hierarchy KW - pattern_recognition KW - visual_cortex AU - George, Dileep AU - Hawkins, Jeff PY - 2005/12/27/ UR - http://dx.doi.org/10.1109/IJCNN.2005.1556155 ER -