Abstract
In this chapter we consider three extensions to Canonical Correlation Analysis networks
-
We derive a nonlinear CCA network for use where the highest correlations are found from nonlinear projections.
-
Using the idea of kernel operations derived from Support Vector Machines, we derive two kernel CCA method and show that one is much to be preferred over the other.
-
We show that a mixture of CCA networks can be used where a locally linear set of correlations varies in time or space.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Rights and permissions
Copyright information
© 2005 Springer-Verlag London Limited
About this chapter
Cite this chapter
(2005). Kernel and Nonlinear Correlations. In: Hebbian Learning and Negative Feedback Networks. Advanced Information and Knowledge Processing. Springer, London. https://doi.org/10.1007/1-84628-118-0_11
Download citation
DOI: https://doi.org/10.1007/1-84628-118-0_11
Publisher Name: Springer, London
Print ISBN: 978-1-85233-883-1
Online ISBN: 978-1-84628-118-1
eBook Packages: Computer ScienceComputer Science (R0)