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

Nonholonomic orthogonal learning algorithms for blind source separation.

S Amari1, T P Chen, A Cichocki

  • 1RIKEN Brain Science Institute, Brain-Style Information Systems Group, Japan.

Neural Computation
|August 10, 2000
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

An Area- and Energy-Efficient Spiking Neural Network With Spike-Time-Dependent Plasticity Realized With SRAM Processing-in-Memory Macro and On-Chip Unsupervised Learning.

IEEE transactions on biomedical circuits and systems·2023
Same author

Braille recognition by E-skin system based on binary memristive neural network.

Scientific reports·2023
Same author

A dynamic AES cryptosystem based on memristive neural network.

Scientific reports·2022
Same author

Evidence of presolar SiC in the Allende <i>Curious Marie</i> calcium aluminum rich inclusion.

Nature astronomy·2020
Same author

[A novel mutation of the LYST gene in a Chinese family with Chediak-Higashi syndrome].

Zhonghua er ke za zhi = Chinese journal of pediatrics·2019
Same author

Sharp selective scattering of red, green, and blue light achieved via gain material's loss compensation.

Optics express·2019
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study introduces novel nonholonomic constraints for blind source separation, improving numerical stability with nonstationary signals. The new method effectively handles scale indeterminacy and overestimation of source numbers in independent component analysis.

Area of Science:

  • Signal Processing
  • Machine Learning
  • Computational Neuroscience

Background:

  • Independent component analysis (ICA) or blind source separation (BSS) recovers independent signals from linear mixtures.
  • Existing ICA algorithms struggle with scale indeterminacy, especially for nonstationary signals with rapidly changing magnitudes.
  • Current methods often impose constraints leading to numerical instability in applications like speech processing and EEG analysis.

Purpose of the Study:

  • To develop a more numerically stable learning algorithm for blind source separation.
  • To address the challenge of scale indeterminacy in ICA, particularly for nonstationary source signals.
  • To improve the robustness of ICA algorithms when the number of sources is overestimated.

Main Methods:

Related Experiment Videos

  • Introduction of novel nonholonomic constraints into the ICA learning algorithm.
  • Geometric considerations guiding the orthogonality of separating matrix changes to equivalence classes.
  • Validation through computer simulations to assess performance and stability.

    • Main Results:

    • The proposed algorithm demonstrates enhanced adaptability to rapid or intermittent changes in source signal magnitudes.
    • Nonholonomic constraints resolve numerical instability issues associated with traditional magnitude constraints.
    • The algorithm performs well even when the number of sources is overestimated, unlike existing methods.

    Conclusions:

    • The novel nonholonomic constraints provide a robust solution for scale indeterminacy in blind source separation.
    • The developed algorithm offers improved numerical stability and reliability for nonstationary signals.
    • This approach enhances the practical applicability of independent component analysis in diverse fields.