Abstract
The aim of this paper is to present a new class of learning models for linear as well as non-linear neural layers called Orthonormal Strongly-Constrained (SOC or Stiefel). They allow to solve orthonormal problems where orthonormal matrices are involved. After general properties of the learning rules belonging to this new class are shown, examples derived independently or by reviewing learning theories known from the literature are presented and discussed.
This work was supported by the Italian MURST.
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.
References
P. Comon, Independent Component Analysis, A New Concept?, Signal Processing, Vol. 36, pp. 287–314, 1994
G. Deco AND W. Brauer, Nonlinear Higher-Order Statistical Decorrelation by Volume-Conserving Neural Architectures, Neural Networks, Vol. 8, No. 4, pp. 525–535, 1995
S. Fiori, Unsupervised Neural Artificial Learning Models for Blind Signal Processing, M.Sc. Dissertation, Dept. of Electronics and Automatics, Univ. of Ancona (Italy), July 1996 (in italian)
S. Fiori, A. Uncini AND F. Piazza, Mechanical Learning Applied to Principal Component Analysis and Source Separation, Artificial Neural Networks, pp. 571–577, 1997, Springer-Verlag
S. Fiori AND F. Piazza, Orthonormal Strongly-Constrained Neural Learning, Proc. of IJCNN, pp. 2332–2337, 1998
C. Fyfe, A General Exploratory Projection Pursuit Network, Neural Processing Letters, Vol. 2, No. 3, 1995
J.F. Cardoso AND B. Laheld, Equivariant Adaptive Source Separation, IEEE Trans. on Signal Processing, Vol. 44, No. 12, pp. 3017–3030, Dec. 1996
E. Moreau AND J.C. Pesquet, Independence/Decorrelation Measures with Application to Optimized Orthonormal Representations, Proc. of ICASSP, pp. 3425–3428, 1997
E. Oja, Neural Networks, Principal Components, and Subspaces, International Journal of Neural System, Vol. 1, pp. 61–68, 1989
F. Palmieri, J. Zhu AND C. Chang, Anti-Hebbian Learning in Topologically Constrained Linear Networks: A Tutorial, IEEE Trans. Neural Networks, Vol. 4, No. 5, pp. 748–761, 1993
L. Xu, Theories for Unsupervised Learning: PCA and Its Nonlinear Extension, Proc. of IJCNN, pp. 1252–1257, 1994
W.-Y. Yan, U. Helmke, AND J.B. Moore, Global Analysis of Oja’s Flow for Neural Networks, IEEE Trans. Neural Networks, Vol. 5, No. 5, pp. 674–683, 1994
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag London Limited
About this paper
Cite this paper
Fiori, S., Uncini, A., Piazza, F. (1999). Neural Learning and Weight Flow on Stiefel Manifold. In: Marinaro, M., Tagliaferri, R. (eds) Neural Nets WIRN VIETRI-98. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-0811-5_36
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0811-5_36
Publisher Name: Springer, London
Print ISBN: 978-1-4471-1208-2
Online ISBN: 978-1-4471-0811-5
eBook Packages: Springer Book Archive