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

How initial conditions affect generalization performance in large networks.

A Atiya1, C Ji

  • 1Dept. of Comput. Eng., Cairo Univ., Giza.

IEEE Transactions on Neural Networks
|January 1, 1997
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

Sleep disturbance and brain health in professional association footballers.

Frontiers in sports and active living·2026
Same author

[Survey on the current status of hospitalized heart failure patients in China, 2023-2024].

Zhonghua xin xue guan bing za zhi·2026
Same author

[Evaluation of changes in serum measles antibody levels in children with tumors before and after chemotherapy and the necessity of revaccination with measles-containing vaccines].

Zhonghua yi xue za zhi·2025
Same author

[Genetic factors for risk stratification in dilated cardiomyopathy].

Zhonghua xin xue guan bing za zhi·2025
Same author

Alcohol, Anti-HIV Drugs, and/or Hippuric Acid Deteriorate Cellular Stresses in Senescent Hepatocytes and Aging Murine Liver.

Journal of addiction & prevention·2025
Same author

Development of linear IgA bullous dermatosis in a patient during an exacerbation of psoriasis.

Annales de dermatologie et de venereologie·2025
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

Initial weight distribution significantly impacts neural network generalization. Small initial weights act as a regularization factor, leading to lower network complexity and improved performance.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Generalization is a critical challenge in neural network research.
  • Network design factors like size and weight decay influence generalization.
  • Understanding generalization is key to developing more robust AI models.

Purpose of the Study:

  • To investigate the impact of initial weight distribution on neural network generalization.
  • To identify initial weight distribution as a key factor influencing generalization.
  • To propose a novel measure for network complexity.

Main Methods:

  • Analyzing the effect of initial weight distribution in gradient descent training algorithms.
  • Examining how initial conditions guide the weight space search.

Related Experiment Videos

  • Developing and applying a new network complexity measure.

    • Main Results:

    • Initial weight distribution is shown to be a significant factor in generalization.
    • Small initial weights tend to produce networks with lower complexity.
    • This lower complexity effectively acts as a regularization factor.

    Conclusions:

    • Initial weight distribution is a crucial, yet often overlooked, factor in achieving good generalization.
    • The proposed network complexity measure offers new insights into generalization phenomena.
    • Findings can guide the design of neural networks with enhanced generalization capabilities.