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

Blind source separation and deconvolution: the dynamic component analysis algorithm

H Attias1, C E Schreiner

  • 1Sloan Center for Theoretical Neurobiology, University of California, San Francisco 94143-0444, USA.

Neural Computation
|August 11, 1998
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

Functional congruity in local auditory cortical microcircuits.

Neuroscience·2016
Same author

Strategies for optical control and simultaneous electrical readout of extended cortical circuits.

Journal of neuroscience methods·2015
Same author

Two thalamic pathways to primary auditory cortex.

Neuroscience·2008
Same author

Perinatal exposure to a noncoplanar polychlorinated biphenyl alters tonotopy, receptive fields, and plasticity in rat primary auditory cortex.

Proceedings of the National Academy of Sciences of the United States of America·2007
Same author

Unbalanced synaptic inhibition can create intensity-tuned auditory cortex neurons.

Neuroscience·2007
Same author

Tonotopic and heterotopic projection systems in physiologically defined auditory cortex.

Neuroscience·2004
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

We developed new unsupervised learning algorithms for separating mixed signals. These methods use spatiotemporal statistics to effectively separate convolutive and instantaneous mixtures, improving upon existing techniques.

Area of Science:

  • Signal Processing
  • Machine Learning
  • Unsupervised Learning

Background:

  • Blind source separation is challenging for mixed and convolved signals.
  • Existing methods like Independent Component Analysis (ICA) have limitations with convolutive mixtures.

Purpose of the Study:

  • To develop novel unsupervised learning algorithms for blind separation of convolutive mixtures.
  • To generalize ICA to handle more complex signal mixtures.
  • To improve the performance and efficiency of source separation techniques.

Main Methods:

  • Formulating separation as a spatiotemporal generative model learning task.
  • Iteratively adapting model parameters to minimize error functions for stable algorithms.
  • Exploiting high-order spatiotemporal statistics of mixture data.

Related Experiment Videos

  • Developing hybrid frequency-time domain models for optimal performance.
  • Extending relative-gradient concepts for equivariant learning rules.

    • Main Results:

    • Algorithms successfully separate instantaneous and convolutive mixtures of speech and noise.
    • Hybrid frequency-time models demonstrate superior performance.
    • Developed fast, efficient, and stable learning rules.
    • Demonstrated equivalence to information-rate maximization.
    • Introduced a semiblind separation method incorporating prior mixing information.

    Conclusions:

    • The novel algorithms provide a robust solution for blind source separation of convolutive mixtures.
    • The approach offers a significant advancement over traditional ICA for complex signal scenarios.
    • The developed methods are efficient, stable, and adaptable to varying levels of prior information.