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

A note on Lewicki-Sejnowski gradient for learning overcomplete representations.

Zhaoshui He1, Shengli Xie, Liqing Zhang

  • 1School of Electronics and Information Engineering, South China University of Technology, Guangzhou, 510640, China. zhshhe@scut.edu.cn

Neural Computation
|December 1, 2007
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

Non-invasive assessment of glymphatic dysfunction in middle cerebral artery stenosis based on DTI-ALPS and ro-ALPS.

Frontiers in neurology·2026
Same author

CancerSubtyper: a deep learning framework for cancer subtyping through DNA methylation data.

Epigenetics & chromatin·2026
Same author

Correction to: The Cerebrovascular Reactivity Adjusted Fractional Amplitude of Low-Frequency Fluctuations Abnormalities in Middle Cerebral Artery Stenosis and Occlusive Disease.

Translational stroke research·2026
Same author

Research on Pathological Voice Recognition Based on XGBoost.

Journal of visualized experiments : JoVE·2026
Same author

Assessment of cerebrovascular reactivity in middle cerebral artery stenosis using non-hypercapnic resting-state fMRI: a potential biomarker for hemodynamic alterations.

BMC medical imaging·2026
Same author

EDSF-Net : An enhanced dynamic spatiotemporal-frequency attention network for robust EEG decoding in motor imagery.

Neural networks : the official journal of the International Neural Network Society·2026
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 provides a rigorous mathematical proof for the overcomplete representation gradient proposed by Lewicki and Sejnowski. A more robust constrained gradient is also introduced for improved performance in noisy environments.

Area of Science:

  • Computational neuroscience
  • Machine learning
  • Signal processing

Background:

  • Overcomplete representations offer enhanced robustness to noise and data structure matching.
  • Lewicki and Sejnowski (2000) introduced an efficient extended natural gradient for learning overcomplete bases, but relied on approximations and complex proofs.

Purpose of the Study:

  • To provide a rigorous mathematical proof for the Lewicki-Sejnowski gradient.
  • To introduce a more robust constrained gradient for overcomplete representations.

Main Methods:

  • Mathematical derivation of the extended natural gradient.
  • Development of a constrained optimization approach for gradient learning.

Main Results:

  • A brief and rigorous mathematical proof for the Lewicki-Sejnowski gradient is presented.

Related Experiment Videos

  • A novel, more robust constrained Lewicki-Sejnowski gradient is proposed.

    • Conclusions:

    • The study strengthens the theoretical foundation of overcomplete representation learning.
    • The proposed constrained gradient offers improved robustness, particularly in noisy conditions.