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

Bootstrapping neural networks.

J Franke1, M H Neumann

  • 1Department of Mathematics, University of Kaiserslautern, 67653 Kaiserslautern, Germany.

Neural Computation
|August 23, 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

Status and future of modern technologies in arthroplasty : Results of a survey of the German Society for Orthopedics and Trauma Surgery (DGOU).

Orthopadie (Heidelberg, Germany)·2022
Same author

Revealing four decades of snow cover dynamics in the Hindu Kush Himalaya.

Scientific reports·2022
Same author

Author Correction: Statistical determinants of visuomotor adaptation along different dimensions during naturalistic 3D reaches.

Scientific reports·2022
Same author

Statistical determinants of visuomotor adaptation along different dimensions during naturalistic 3D reaches.

Scientific reports·2022
Same author

Mechanical modifications of soft actuators for the use as a dynamic iris implant.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2021
Same author

Intraurethral Energy Harvesting from Urine Flow as an Approach to Power Urologic Implants.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2021
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

The bootstrap method accurately estimates statistical distributions for artificial neural networks. This research confirms its consistency for parameter estimation in neural network models.

Area of Science:

  • Computational Statistics
  • Machine Learning
  • Artificial Intelligence

Background:

  • Understanding statistical estimator distributions is crucial for confidence intervals and hypothesis testing.
  • The bootstrap method is a common technique for estimating these distributions by resampling data.
  • Artificial neural networks are increasingly used for complex input-output mapping estimations.

Purpose of the Study:

  • To investigate the applicability and consistency of the bootstrap method in the context of artificial neural networks.
  • To provide theoretical grounding for using bootstrap estimates in neural network parameter analysis.

Main Methods:

  • The study employs theoretical analysis to examine the bootstrap method's behavior.
  • Focuses on artificial neural networks as the model for estimating input-output mappings.

Related Experiment Videos

  • Derives consistency results for bootstrap-based distribution estimates of model parameters.

    • Main Results:

    • Established theoretical consistency for bootstrap estimates of parameter distributions in artificial neural networks.
    • Demonstrates that the bootstrap method reliably approximates the true distribution of parameter estimates.

    Conclusions:

    • The bootstrap method is a valid and consistent approach for assessing the uncertainty of parameter estimates in neural networks.
    • Findings support the use of bootstrap techniques for statistical inference in deep learning models.