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

Thresholding neural network for adaptive noise reduction.

X P Zhang1

  • 1Department of Electrical and Computer Engineering, Ryerson Polytechnic University, Toronto, ON M5B 2K3, Canada. xpzhang@ieee.org

IEEE Transactions on Neural Networks
|February 6, 2008
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

[Direct medical costs and influencing factors of pertussis cases in children in Zhejiang Province].

Zhonghua yu fang yi xue za zhi [Chinese journal of preventive medicine]·2026
Same author

First Detection of Ultrahigh Energy Emission from Gamma-Ray Binary LS I +61° 303.

Physical review letters·2026
Same author

Evidence of Cosmic-Ray Acceleration up to Sub-PeV Energies in the Supernova Remnant IC 443.

Physical review letters·2026
Same author

[The paradigm shift in perioperative treatment strategies for gastric cancer in the era of precision therapy].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2026
Same author

Precise Measurement of the Cosmic Ray Helium Spectrum above 0.1 PeV.

Physical review letters·2026
Same author

All-Sky Search for Individual Primordial Black Hole Bursts with LHAASO.

Physical review letters·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

A novel thresholding neural network (TNN) was developed for adaptive noise reduction using new, infinitely differentiable thresholding functions. This TNN, particularly with stochastic learning, offers superior nonlinear adaptive filtering performance compared to linear methods.

Area of Science:

  • Artificial Intelligence
  • Signal Processing
  • Machine Learning

Background:

  • Adaptive noise reduction is crucial in signal processing.
  • Existing thresholding functions limit gradient-based learning in neural networks.
  • Linear methods often fall short in complex noise reduction scenarios.

Purpose of the Study:

  • To develop a novel thresholding neural network (TNN) for adaptive noise reduction.
  • To introduce new, infinitely differentiable soft and hard thresholding functions for TNN activation.
  • To explore gradient-based learning algorithms and analyze the performance of TNNs.

Main Methods:

  • Development of new soft and hard thresholding functions as TNN activation functions.
  • Analysis of optimal solutions in the mean square error (MSE) sense for TNNs.

Related Experiment Videos

  • Implementation of supervised and unsupervised batch and stochastic gradient-based learning algorithms.
  • Comparison of TNN performance against linear noise reduction methods.

    • Main Results:

    • New thresholding functions enable effective gradient-based learning.
    • TNNs demonstrate effectiveness in finding optimal thresholding solutions (MSE sense).
    • TNN-based nonlinear adaptive filtering outperforms conventional linear adaptive filtering.

    Conclusions:

    • The developed TNN with novel activation functions is effective for adaptive noise reduction.
    • Stochastic learning algorithms allow TNNs to function as novel nonlinear adaptive filters.
    • TNNs provide superior performance over linear methods in both optimal solutions and learning.