Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

The fastICA algorithm revisited: convergence analysis.

Erkki Oja1, Zhijian Yuan

  • 1Adaptive Informatics Research Centre, Helsinki University of Technology, 02015 HUT, Finland. erkki.oja@hut.fi

IEEE Transactions on Neural Networks
|November 30, 2006
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Gardeniae Fructus extract terminates refractory status epilepticus with a wide time window through inhibiting neuroinflammation.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2025
Same author

New advances in Traditional Chinese Medicine interventions for epilepsy: where are we and what do we know?

Chinese medicine·2025
Same author

Low-Frequency Stimulation at the Ventromedial Hypothalamus Exhibits Broad-Spectrum Efficacy Across Models of Epilepsy.

CNS neuroscience & therapeutics·2025
Same author

Learning the Information Divergence.

IEEE transactions on pattern analysis and machine intelligence·2015
Same author

Effect of fat particle-to-SVF ratio on graft survival rates in rabbits.

Annals of plastic surgery·2013
Same author

BSS and ICA in neuroinformatics: from current practices to open challenges.

IEEE reviews in biomedical engineering·2012
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

The FastICA algorithm

Area of Science:

  • Signal Processing
  • Machine Learning
  • Data Analysis

Background:

  • Independent Component Analysis (ICA) is crucial for blind source separation.
  • The FastICA algorithm is a popular and fast ICA method.
  • Previous convergence analysis focused on a simplified one-unit case.

Purpose of the Study:

  • To analyze the convergence of the full FastICA algorithm with symmetrical normalization.
  • To determine if normalization affects the algorithm's convergence speed.
  • To validate theoretical findings with numerical simulations.

Main Methods:

  • Local convergence analysis for the general FastICA algorithm.
  • Inclusion of the explicit normalization step in the analysis.
  • Numerical illustration of global behavior for a two-source, two-mixture scenario.

Related Experiment Videos

Main Results:

  • The symmetrical normalization step does not negatively impact FastICA's convergence speed.
  • The convergence properties observed in the one-unit case extend to the full algorithm.
  • Numerical results support the theoretical convergence analysis.

Conclusions:

  • The FastICA algorithm with symmetrical normalization maintains excellent convergence properties.
  • Theoretical analysis confirms the robustness of FastICA's speed.
  • The study provides a comprehensive understanding of FastICA's convergence behavior.