The Community for Technology Leaders
Neural Networks, Brazilian Symposium on (2012)
Curitiba, Parana, Brazil Brazil
Oct. 20, 2012 to Oct. 25, 2012
ISSN: 1522-4899
ISBN: 978-1-4673-2641-4
pp: 131-135
ABSTRACT
This paper presents a new probabilistic hierarchical model, called HIGMN (Hierarchical Incremental Gaussian Mixture Network), which is based on ideas presented by Deep Architectures. The proposed model, composed by layers of IGMNs, is able to extract features from data input of different domains in the low-level layers and to correlate these features in a high-level layer. Experiments show that HIGMN is able to learn an abstract behavior using the features extracted from sensory and motor data of a mobile robot and to perform correct actions even in unknown instances of sensory perception.
INDEX TERMS
Robotics, Hierarchical Incremental Gaussian Mixture Network, Deep Learning, HIGMN, IGMN, Probabilistic Models
CITATION

R. de Pontes Pereira, P. M. Engel and R. C. Pinto, "Learning Abstract Behaviors with the Hierarchical Incremental Gaussian Mixture Network," 2012 Brazilian Symposium on Neural Networks (SBRN 2012)(SBRN), Curitiba, 2012, pp. 131-135.
doi:10.1109/SBRN.2012.30
97 ms
(Ver 3.3 (11022016))