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

Optimization for training neural nets.

E Barnard1

  • 1Dept. of Electron. and Comput. Eng., Pretoria Univ.

IEEE Transactions on Neural Networks
|January 1, 1992
PubMed
Summary
This summary is machine-generated.

A new stochastic technique for training neural-net classifiers is superior for large datasets. Standard deterministic methods like variable metric and conjugate gradient show similar convergence rates.

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

Consent and Chaperone Practices in Transvaginal Ultrasound: Exploring Sonographer Knowledge, Gender, and Ethical Challenges.

Irish medical journal·2026
Same author

Clinical, tactical and strategic benefits of a UK Spray Dried Plasma production capability.

BMJ military health·2025
Same author

Oral tranexamic acid as a preferred administration route for severe trauma in the extreme cold weather environment.

BMJ military health·2025
Same author

'Golden day' is a myth: rethinking medical timelines and risk in large scale combat operations.

BMJ military health·2024
Same author

Prehospital emergency care in a humanitarian environment: an overview of the ethical considerations.

BMJ military health·2023
Same author

Red cell haemolysis secondary to intraosseous (IO) blood transfusion in adult patients with major trauma: a systematic review.

BMJ military health·2023
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

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Computer Science

Background:

  • Training neural networks involves optimizing complex criterion functions.
  • Efficient optimization is crucial for classifier performance, especially with large datasets.

Purpose of the Study:

  • To investigate and compare the effectiveness of various optimization techniques for training neural-net classifiers.
  • To identify the most suitable methods for different problem scales.

Main Methods:

  • Comparison of three standard deterministic optimization techniques: variable metric, conjugate gradient, and steepest descent.
  • Introduction and evaluation of a novel stochastic optimization technique.
  • Empirical analysis on problems with varying training set sizes.

Related Experiment Videos

Main Results:

  • The stochastic technique demonstrates superior performance on large training sets.
  • Variable metric and conjugate gradient methods exhibit comparable convergence rates.
  • Steepest descent's performance relative to other methods is not explicitly detailed but implied as less efficient for large sets.

Conclusions:

  • Stochastic optimization is recommended for large-scale neural network training.
  • Variable metric and conjugate gradient are viable alternatives with similar efficiency.
  • Further research may explore hybrid approaches or adaptive methods.