Abstract
A new learning rule is implemented for approximating canonical correlation analysis(CCA) with artificial neural networks. A correlation objective function is maximized in order to find identical or correlated item from several sets of data. A simple weight update rule is derived, that is computationally much more inexpensive than the standard statistical technique. We demonstrate the network capabilities on artificial and real-world data. The experimental results show that this method is a good approximator of CCA as well as correlated item identifier.
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
Charles, D., Fyfe, C.: Modeling multiple cause structure using rectification constraints. Networks: Computation in Neural Systems 9, 167–182 (1998)
Fyfe, C., Baddeley, R.: Non-linear data structure extracting using simple habbian networks. Biological Cybernetics 72(6), 533–541 (1995)
Hyverinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. John Wiley & Sons Publishing, USA (2001)
Lai, P.L., Fyfe, C.: A neural implementation of canonical correlation analysis. Neural Networks 12, 1391–1397 (1999)
Mardia, K.V., Kent, J., Bibby: Multivariate analysis. Academic Press, New York (1979)
Oja, E.: A simplified neuron model as a principle component analyzer. Journal of Mathematical Biology 16, 267–273 (1982)
Oja, E.: The nonlinear pca learning rule in independent component analysis. Neurocomputing 17, 25–45 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Shahjahan, M., Murase, K. (2004). A Neural Learning Rule for CCA Approximation. In: Pal, N.R., Kasabov, N., Mudi, R.K., Pal, S., Parui, S.K. (eds) Neural Information Processing. ICONIP 2004. Lecture Notes in Computer Science, vol 3316. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30499-9_71
Download citation
DOI: https://doi.org/10.1007/978-3-540-30499-9_71
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23931-4
Online ISBN: 978-3-540-30499-9
eBook Packages: Springer Book Archive