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

Learning overcomplete representations.

M S Lewicki1, T J Sejnowski

  • 1Computer Science Dept. and Center for the Neural Basis of Cognition, Carnegie Mellon Univ., 115 Mellon Inst., Pittsburgh, PA 15213, USA.

Neural Computation
|January 15, 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

Presynaptic vesicles supply membrane for axonal bouton enlargement during LTP.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2026
Same author

Presynaptic vesicles supply membrane for axonal bouton enlargement during LTP.

bioRxiv : the preprint server for biology·2025
Same author

Stochastic self-tuning hybrid algorithm for reaction-diffusion systems.

The Journal of chemical physics·2020
Same author

A path toward understanding neurodegeneration.

Science (New York, N.Y.)·2016
Same author

Disruption of mGluR5 in parvalbumin-positive interneurons induces core features of neurodevelopmental disorders.

Molecular psychiatry·2015
Same author

Monitoring Spiking Activity of Many Individual Neurons in Invertebrate Ganglia.

Advances in experimental medicine and biology·2015
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 a new algorithm for learning overcomplete bases, enhancing data representation efficiency and robustness. The method improves signal approximation and coding efficiency, generalizing independent component analysis for noise-robust reconstruction and blind source separation.

Area of Science:

  • Computational neuroscience
  • Machine learning
  • Signal processing

Background:

  • Overcomplete representations offer robustness, sparsity, and flexibility in data analysis.
  • Existing methods focus on using fixed overcomplete bases, limiting adaptability.
  • Overcomplete codes are relevant to neural responses in the visual cortex.

Purpose of the Study:

  • To develop an algorithm for learning overcomplete bases from data.
  • To improve data representation by better approximating underlying statistical distributions.
  • To generalize existing techniques like independent component analysis.

Main Methods:

  • A probabilistic model approach is used to learn the overcomplete basis.
  • The algorithm aims to find a basis that yields a better approximation of data distributions.

Related Experiment Videos

  • This method is framed as a generalization of independent component analysis.

    • Main Results:

    • Learned overcomplete bases provide a better approximation of data's statistical distribution.
    • The approach leads to enhanced coding efficiency compared to fixed bases.
    • The algorithm facilitates Bayesian signal reconstruction and blind source separation.

    Conclusions:

    • Learning overcomplete bases offers significant advantages in data representation and efficiency.
    • The proposed method generalizes independent component analysis, enabling robust signal processing.
    • This approach has implications for understanding neural coding and improving signal separation techniques.