Unsupervised Bayesian Network Learning for Object Recognition in Image Sequences

Authors:
Daniel Oberhoff;Marina Kolesnik
Affiliations:
Fraunhofer Institut FIT, Schloss Birlinghoven, Sankt Augustin 53754;Fraunhofer Institut FIT, Schloss Birlinghoven, Sankt Augustin 53754
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Year:
2008

Citing 4
Cited 0

Variational Message Passing

The Journal of Machine Learning Research
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
Learning invariant features using inertial priors

Annals of Mathematics and Artificial Intelligence
A computational model of the cerebral cortex

AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2

Quantified Score

Hi-index	0.00

Visualization

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.