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

On different facets of regularization theory.

Zhe Chen1, Simon Haykin

  • 1Adaptive Systems Lab, Communications Research Laboratory, McMaster University, Hamilton, Ontario, Canada L8S 4K1. zhechen@soma.crl.mcmaster.ca

Neural Computation
|December 19, 2002
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

AntimiR-30b Inhibits TNF-α Mediated Apoptosis and Attenuated Cartilage Degradation through Enhancing Autophagy.

Cellular physiology and biochemistry : international journal of experimental cellular physiology, biochemistry, and pharmacology·2016
Same author

Noncontact Synergistic Effect between Au Nanoparticles and the Fe<sub>2</sub>O<sub>3</sub> Spindle Inside a Mesoporous Silica Shell as Studied by the Fenton-like Reaction.

Langmuir : the ACS journal of surfaces and colloids·2016
Same author

An elaborate landscape of the human antibody repertoire against enterovirus 71 infection is revealed by phage display screening and deep sequencing.

mAbs·2016
Same author

The role of size of input box, location of input box, input method and display size in Chinese handwriting performance and preference on mobile devices.

Applied ergonomics·2016
Same author

Apelin/APJ System: A Novel Therapeutic Target for Myocardial Ischemia/Reperfusion Injury.

DNA and cell biology·2016
Same author

A New Soft Computing Method for K-Harmonic Means Clustering.

PloS one·2016
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 review explores regularization theory, highlighting smoothness and simplicity. It connects Tikhonov regularization to operator theory and Fourier analysis, reviewing diverse research areas for broader applications.

Area of Science:

  • Mathematics
  • Computer Science
  • Information Theory

Background:

  • Regularization theory is crucial for solving ill-posed problems in various scientific domains.
  • Classical Tikhonov regularization is a foundational method, but understanding its theoretical underpinnings from multiple perspectives is essential.
  • Existing research spans diverse fields, necessitating a unified review of regularization principles.

Purpose of the Study:

  • To provide a comprehensive understanding of regularization theory from multiple viewpoints.
  • To connect classical regularization methods with advanced mathematical tools.
  • To review state-of-the-art research and suggest future directions in regularization.

Main Methods:

  • Utilizes operator theory and Fourier analysis to derive Tikhonov regularization solutions.

Related Experiment Videos

  • Reviews and synthesizes research from fields including information theory, statistical learning, and algorithmic approaches.
  • Discusses regularization principles in the context of Kolmogorov complexity.

    • Main Results:

    • Demonstrates the derivation of Tikhonov regularization solutions via linear operators in spatial and Fourier domains.
    • Synthesizes diverse regularization concepts, including Occam's razor, minimum description length, and Bayesian inference.
    • Highlights the universal principle of regularization through Kolmogorov complexity.

    Conclusions:

    • Regularization theory can be understood through the lens of smoothness and simplicity, unified by mathematical and informational principles.
    • The review provides a broad perspective on regularization, bridging classical methods with modern theoretical frameworks.
    • Identifies potential future research avenues in regularization theory and its applications.