Abstract
We present work on the learning of hierarchical Bayesian networks for image recognition tasks. We employ Bayesian priors to the parameters to avoid over-fitting and variational learning. We further explore the effect of embedding Hidden Markov Models with adjusted priors to perform sequence based grouping, and two different learning strategies, one of which can be seen as a first step towards online-learning. Results on a simple data-set show, that the simplest network and learning strategy work best, but that the penalty for the more complex models is reasonable, encouraging work on more complex problems.
Supported by the EC, Contract No.: 12963 NEST, project MCCOOP.
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
Fukushima, K.: Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cyb. V36(4), 193–202 (1980)
Riesenhuber, M., Poggio, T.: 11: How Visual Cortex Recognizes Objects: The Tale of the Standard Model. In: Computational Object Vision, pp. 1640–1653 (2003)
Osindero, S., Hinton, G.E.: Modeling image patches with a directed hierarchy of markov random fields. Advances in Neural Processing Systems 20 (2008)
Dean, T.: A computational model of the cerebral cortex. In: Proc. 20th Nat. Conf. on Art. Intell. MIT Press, Cambridge (2005)
Dean, T.: Learning invariant features using inertial priors. Annals of Mathematics and Artificial Intelligence 47, 223–250 (2006)
Dean, T.: Scalable inference in hierarchical generative models. Ann. Art. Intell. & Math.
Deco, G., Rolls, E.T.: A neurodynamical cortical model of visual attention and invariant object recognition. Vis. Res. 44 (2004)
Masquelier, T., Serre, T., Thorpe, S., Poggio, T.: Learning complex cell invariance from natural videos: a plausibility proof. Technical report, Massachusetts Institute of Technology, Cambridge, MA (2007)
Berkes, P., Wiskott, L.: Slow feature analysis yields a rich repertoire of complex cell properties. J. o. Vis. 5/6/9 (2003)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2006)
Beal, M.J.: Variational Algorithms or Approximate Bayesian Inference. PhD thesis, University of Cambridge, UK (2003)
Winn, J.M., Bishop, C.M.: Variational message passing. J. Mach. L. Res. 6, 558–590 (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Oberhoff, D., Kolesnik, M. (2008). Unsupervised Bayesian Network Learning for Object Recognition in Image Sequences. In: Kůrková, V., Neruda, R., KoutnÃk, J. (eds) Artificial Neural Networks - ICANN 2008. ICANN 2008. Lecture Notes in Computer Science, vol 5163. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87536-9_25
Download citation
DOI: https://doi.org/10.1007/978-3-540-87536-9_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87535-2
Online ISBN: 978-3-540-87536-9
eBook Packages: Computer ScienceComputer Science (R0)