Abstract
This paper proposes a neural network structure as well as an adaptation of the backpropagation algorithm for its training that provides a way to consider multidimensional information directly in its original space. Traditionally, when inputting multidimensional information to artificial neural networks, its components are fed individually through different inputs and basically processed separately throughout the network. In the present structure, the multidimensional information, in the form of vectors is processed as such in the network, thus preserving in a simple way all the multidimensional neighbourhood relationships. The projection into the dimensionality of the output space is also carried out within the network. This procedure allows for a simpler processing of multidimensional signals such as multi or hyperspectral cubes as used in remote sensing or colour signals in images, which is the example we present as a test for the algorithm.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Fiesler, E., Beale, R. (eds. in chief): Handbook of Neural Computation, pp. B1.7:2–B1.7:3. IOP Publishing Ltd. and Oxford University Press (1997)
Duro, R.J., Crespo, J.L., Santos, J.: Training Higher Order Gaussian Synapses. In: Mira, J. (ed.) IWANN 1999. LNCS, vol. 1606, pp. 537–545. Springer, Heidelberg (1999)
Buchholz, S., Sommer, G.: A Hyperbolic Multilayer Perceptron. In: Proceedings of the International Joint Conference on Artificial Neural Networks IJCNN2000, Como (Italy), vol. 2, pp. 129–133 (2000)
Buchholz, S., Sommer, G.: Quaternionic spinor MLP. In: Proceedings of the 8th European Symposium on Artificial Neural Networks ESANN2000, Bruges (Belgium), pp. 377–382 (2000)
Neural Networks in Multidimensional Domains. LNCIS, vol. 234. Springer, Heidelberg (1998)
Duch, W., Jankowski, N.: Survey of Neural Transfer Functions. Neural Computer Surveys 2, 163–213 (1999)
Verleysen, M., Francois, D., Simon, G., Wertz, V.: On the Effects of Dimensionality on Data Analysis with Neural Networks. In: Mira, J., Alvarez, J.R. (eds.) Artificial Neural Nets Problem solving Methods, vol. 2, pp. 105–112. Springer, Heidelberg (2003)
Red Neuronal Artificial Vectorial basada en Sinapsis Gaussianas de alto Orden. GSA Internal Report. Ref: 01/06-(2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Crespo, J.L., Duro, R.J. (2005). Considering Multidimensional Information Through Vector Neural Networks. In: Cabestany, J., Prieto, A., Sandoval, F. (eds) Computational Intelligence and Bioinspired Systems. IWANN 2005. Lecture Notes in Computer Science, vol 3512. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11494669_3
Download citation
DOI: https://doi.org/10.1007/11494669_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26208-4
Online ISBN: 978-3-540-32106-4
eBook Packages: Computer ScienceComputer Science (R0)