Abstract
A multi-stream extension of Exploratory Projection Pursuit is proposed as a method for the formation of local, spatiotemporal, oriented filters similar to complex cells found in the visual cortex. This algorithm, which we call the Exploratory Correlation Analysis (ECA) network, is derived to maximise dependencies between separate, but related, data streams. By altering the functions on the outputs of the ECA network we can explore different forms of shared, higher order structure in multiple data streams.
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
K. Okajima, “An information-based learning rule that generates cells similar to visual cortical neurons,” Neural Networks, no. 14, pp. 1173–1180, 2001.
C. Fyfe, “A general exploratory projection pursuit network,” Neural Processing Letters, vol. 2, no. 3, pp. 17–19, May 1995.
Persi Diaconis and David Freedman, “Asymptotics of graphical projections,” The Annals of Statistics, vol. 12, no. 3, pp. 793–815, 1984.
E. Oja, “Neural networks, principal components and subspaces,” International Journal of Neural Systems, vol. 1, pp. 61–68, 1989.
Juha Karhunen and Jyrki Joutsensalo, “Representation and separation of signals using nonlinear pca type learning,” Neural Networks, vol. 7, no. 1, pp. 113–127, 1994.
J. Koetsier, D. Charles, D. MacDonald, and C. Fyfe, “Exploratory correlation analysis,” ESANN 2002, to appear 2002.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Charles, D., Koetsier, J., MacDonald, D., Fyfe, C. (2002). Multi-stream Exploratory Projection Pursuit for the Formation of Complex Cells Similar to Visual Cortical Neurons. In: Dorronsoro, J.R. (eds) Artificial Neural Networks — ICANN 2002. ICANN 2002. Lecture Notes in Computer Science, vol 2415. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46084-5_35
Download citation
DOI: https://doi.org/10.1007/3-540-46084-5_35
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44074-1
Online ISBN: 978-3-540-46084-8
eBook Packages: Springer Book Archive