Compartir
Titre
Rectified Gaussian Distributions and the Formation of Local Filters From Video Data
Autor(es)
Sujet
Computer Science
Fecha de publicación
2001/04
Éditeur
D-Facto public.
Citación
ESANN'2001 proceedings - European Symposium on Artificial Neural Networks. pp. 397-402.
Resumen
We investigate the use of an unsupervised artificial neural network to form a sparse representation of the underlying causes in a data set. By using fixed lateral connections that are derived from the Rectified Generalised Gaussian distribution, we form a network that is capable of identifying multiple cause structure in visual data and grouping similar causes together on the output response of the network. We show that the network may be used to form local spatiotemporal filters in response to real images contained in video data.
URI
https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2001-33.pdf
http://hdl.handle.net/10366/135115
http://hdl.handle.net/10366/135115
ISBN
2-930307-01-3
Aparece en las colecciones
- BISITE. Congresos [232]