Abstract
The FastICA algorithm, a classical method for solving the one-unit linear ICA problem, and its generalisations are studied. Two interpretations of FastICA are provided, a scalar shifted algorithm and an approximate Newton method. Based on these two interpretations, two natural generalisations of FastICA on a full matrix are proposed to solve the parallel linear ICA problem. Specifically, these are a matrix shifted parallel ICA method and an approximate Newton-like parallel ICA method.
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
References
Absil P-A, Mahony R, Sepulchre R (2008) Optimization algorithms on matrix manifolds. Princeton University Press, Princeton
Absil P-A, Mahony R, Sepulchre R, Dooren PV (2002) A Grassmann–Rayleigh quotient iteration for computing invariant subspaces. SIAM Rev 44(1):57–73
Adler R, Dedieu J-P, Margulies J, Martens M, Shub M (2002) Newton’s method on Riemannian manifolds and a geometric model for the human spine. IMA J Numer Anal 22:359–390
Boothby WM (2002) An introduction to differentiable manifolds and Riemannian geometry, revised, 2nd edn. Academic Press, Oxford
Cichocki A, Amari S-I (2002) Adaptive blind signal and image processing: learning algorithms and applications. John Wiley & Sons Ltd., Chichester
Comon P (1994) Independent component analysis, a new concept?. Signal Process 36(3):287–314
Edelman A, Arias TA, Smith ST (1998) The geometry of algorithms with orthogonality constraints. SIAM J Matrix Anal Appl 20(2):303–353
Fiori S (2006) Fixed-point neural independent component analysis algorithms on the orthogonal group. Future Generation Comput Syst 22(4):430–440
Fiori S (2007) Learning independent components on the orthogonal group of matrices by retractions. Neural Process Lett 25(3):187–198
Hüper K, Trumpf J (2004) Newton-like methods for numerical optimisation on manifolds. In: Proceedings of thirty-eighth Asilomar conference on signals, systems and computers, pp 136–139
Hyvärinen A (1999) Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans Neural Netw 10(3):626–634
Hyvärinen A, Karhunen J, Oja E (2001) Independent component analysis. Wiley, New York
Journée M , Absil P-A, Sepulchre R (2007) Gradient-optimization on the orthogonal group for independent component analysis. In: Proceedings of the 7th international conference on independent component analysis and source separation (ICA 2007). Lecture notes in computer science, vol 4666. Springer, Berlin, pp 57–64
Journée M, Teschendorff AE, Absil P-A, Sepulchre R (2007) Geometric optimization methods for independent component analysis applied on gene expression data. In: Proceedings of the 32nd IEEE international conference on acoustics, speech, and signal processing (ICASSP 2007), pp IV1413–IV1416, Hawaii, USA
Kleinsteuber M (2006) Jacobi-type methods on semisimple Lie algebras—a Lie algebraic approach to the symmetric eigenvalue problem. PhD thesis, Bayerische Julius-Maximilians-Universität Würzburg
Kleinsteuber M, Hüper K (2007) An intrinsic CG algorithm for computing dominant subspaces. In: Proceedings of the 32nd IEEE international conference on acoustics, speech, and signal processing (ICASSP 2007), pp IV1405–IV1408, Hawaii, USA
Moler C, van Loan C (2003) Nineteen dubious ways to compute the exponential of a matrix, twenty-five years later. SIAM Rev 45(1):3–49
Nishimori Y (1999) Learning algorithm for ICA by geodesic flows on orthogonal group. In: The International Joint Conference on Neural Networks (IJCNN’99), pp 933–938, Washington, DC, USA
Regalia P, Kofidis E (2003) Monotonic convergence of fixed-point algorithms for ICA. IEEE Trans Neural Netw 14(4):943–949
Roberts S, Everson R (2001) Independent component analysis: principles and practice. Cambridge University Press, Cambridge
Schobben D, Torkkola K, Smaragdis P (1999) Evaluation of blind signal separation methods. In: Proceedings of the 1st international workshop on independent component analysis and blind source separation (ICA 1999), pp 261–266
Shen H, Hüper K (2007) Generalised fastICA for independent subspace analysis. In: Proceedings of the 32nd IEEE international conference on acoustics, speech, and signal processing (ICASSP 2007), pp IV1409–IV1412, Hawaii, USA
Shen H, Kleinsteuber M, Hüper K (2008) Local convergence analysis of FastICA and related algorithms. IEEE Trans Neural Netw 19(6):1022–1032
Shub M (1986) Some remarks on dynamical systems and numerical analysis. In: Dynamical systems and partial differential equations (Caracas, 1984): Proceedings of the VII ELAM pp 69–92, Universidad Simon Bolivar, Caracas
Smith ST (1994) Optimization techniques on Riemannian manifolds. In: Bloch A (ed) Hamiltonian and gradient flows, algorithms and control, Fields Institute Communications. American Mathematical Society, Providence, pp 113–136
Spivak M (1999) A comprehensive introduction to differential geometry, vols 1–5, 3rd edn. Publish or Perish, Inc, Houston
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media B.V.
About this chapter
Cite this chapter
Shen, H., Hüper, K., Kleinsteuber, M. (2011). On FastICA Algorithms and Some Generalisations. In: Van Dooren, P., Bhattacharyya, S., Chan, R., Olshevsky, V., Routray, A. (eds) Numerical Linear Algebra in Signals, Systems and Control. Lecture Notes in Electrical Engineering, vol 80. Springer, Dordrecht. https://doi.org/10.1007/978-94-007-0602-6_19
Download citation
DOI: https://doi.org/10.1007/978-94-007-0602-6_19
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-007-0601-9
Online ISBN: 978-94-007-0602-6
eBook Packages: EngineeringEngineering (R0)