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

Dynamic learning rate optimization of the backpropagation algorithm.

X H Yu1, G A Chen, S X Cheng

  • 1Dept. of Radio Eng., Southeast Univ., Nanjing.

IEEE Transactions on Neural Networks
|January 1, 1995
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

Discovery of an I^{π}=10^{+} Isomer in ^{150}Yb: Nature of the Longest 10^{+} Isomeric Chain.

Physical review letters·2026
Same author

[Efficacy and safety of resection of hilar cholangiocarcinoma with left hepatectomy after pre-operative embolization of the invaded right hepatic artery].

Zhonghua yi xue za zhi·2025
Same author

[Analysis on epidemiology trends of overweight, obesity, and body mass index in adults aged 18-69 years in Shandong Province, 2004-2023].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2025
Same author

[Analysis of the trend changes in the burden of cardiovascular disease mortality in China from 2010 to 2021].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2025
Same author

[Application of CT guided percutaneous interstitial brachytherapy in the treatment of recurrent cervical cancer with isolated lesions in the radiated field].

Zhonghua zhong liu za zhi [Chinese journal of oncology]·2025
Same author

[Preliminary application study of digital technology for constructing three-dimensional facial symmetry reference planes in anterior dental esthetic restoration].

Zhonghua kou qiang yi xue za zhi = Zhonghua kouqiang yixue zazhi = Chinese journal of stomatology·2024
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

This study introduces dynamic learning rate optimization for backpropagation (BP) algorithms, significantly accelerating convergence. The new methods reduce running time by 10-50 times without increasing computational load.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Backpropagation (BP) algorithm efficiency is limited by flat and steep regions in error surfaces.
  • Fixed learning rates in BP lead to slow convergence and reduced performance.

Purpose of the Study:

  • To develop dynamic learning rate optimization for BP using derivative information.
  • To accelerate the convergence of BP algorithms and reduce overall training time.

Main Methods:

  • Explored efficient derivation of first and second derivatives of the objective function concerning the learning rate.
  • Developed optimization approaches using linear expansion, line searches, and Newton-like methods.
  • Introduced simultaneous determination of optimal learning rate and momentum by linking BP with conjugate gradient methods.

Related Experiment Videos

Main Results:

  • Achieved significant acceleration in BP algorithm convergence, reducing running time by 10-50 times.
  • Maintained computational and storage burdens comparable to the standard BP algorithm.
  • Demonstrated effectiveness across various network architectures and applications through computer simulations.

Conclusions:

  • Dynamic learning rate optimization using derivative information enhances BP algorithm efficiency.
  • The proposed methods offer a computationally efficient way to accelerate neural network training.
  • This approach provides a remarkable reduction in training time without compromising network size scalability.