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 Concept Videos

Neural Regulation01:37

Neural Regulation

34.8K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
34.8K
Calibration Curves: Linear Least Squares01:20

Calibration Curves: Linear Least Squares

4.3K
A calibration curve is a plot of the instrument's response against a series of known concentrations of a substance. This curve is used to set the instrument response levels, using the substance and its concentrations as standards. Alternatively, or additionally, an equation is fitted to the calibration curve plot and subsequently used to calculate the unknown concentrations of other samples reliably.
For data that follow a straight line, the standard method for fitting is the linear...
4.3K
Regression Toward the Mean01:52

Regression Toward the Mean

6.3K
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...
6.3K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Deep Learning for Image Watermarking: A Comprehensive Review and Analysis of Techniques, Challenges, and Applications.

Sensors (Basel, Switzerland)·2026
Same author

Design of performance evaluation method for higher education reform based on adaptive fuzzy algorithm.

PeerJ. Computer science·2025
Same author

Bidirectional Multiscale Efficient Dilated Convolutional Recurrent Neural Network Improved by Swarm Intelligence Optimization.

IEEE transactions on neural networks and learning systems·2025
Same author

Patient-Specific Modeling and Model Predictive Control Approach to Personalized Optimal Anemia Management.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2023
Same author

Convergence Analysis of Online Gradient Method for High-Order Neural Networks and Their Sparse Optimization.

IEEE transactions on neural networks and learning systems·2023
Same author

Control-Relevant Adaptive Personalized Modeling From Limited Clinical Data for Precise Warfarin Management.

IEEE open journal of engineering in medicine and biology·2023

Related Experiment Video

Updated: May 5, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

11.0K

Batch gradient method with smoothing L1/2 regularization for training of feedforward neural networks.

Wei Wu1, Qinwei Fan2, Jacek M Zurada3

  • 1School of Mathematical Sciences, Dalian University of Technology, Dalian 116024, PR China.

Neural Networks : the Official Journal of the International Neural Network Society
|December 3, 2013
PubMed
Summary

This study introduces a novel, smoothed L1/2 regularization method for pruning feedforward neural networks. This technique effectively reduces weight oscillations and improves pruning accuracy, ensuring training convergence.

Keywords:
Batch gradient methodConvergenceFeedforward neural networksSmoothing regularization

Related Experiment Videos

Last Updated: May 5, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

11.0K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Deep Learning

Background:

  • Feedforward neural networks (FNNs) require efficient pruning methods to reduce complexity and improve performance.
  • Traditional L1/2 regularization techniques for pruning suffer from gradient oscillations due to non-differentiability at the origin.

Purpose of the Study:

  • To develop a novel and effective method for pruning feedforward neural networks.
  • To address the limitations of conventional L1/2 regularization by introducing a smoothed term.

Main Methods:

  • A modified L1/2 regularization term is introduced into the error function of feedforward neural networks.
  • The regularization term is smoothed at the origin to ensure gradient differentiability.
  • The proposed method is evaluated through numerical examples.

Main Results:

  • The smoothed L1/2 regularization eliminates gradient oscillations during training.
  • The method achieves superior pruning performance, resulting in smaller weights for removal.
  • Convergence of the training process is mathematically proven.

Conclusions:

  • The smoothed L1/2 regularization offers a more stable and effective approach to pruning feedforward neural networks.
  • This novel method enhances model efficiency and accuracy.
  • The technique provides theoretical guarantees for training convergence.