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

Recursive dynamic node creation in multilayer neural networks.

M R Azimi-Sadjadi1, S Sheedvash, F O Trujillo

  • 1Dept. of Electr. Eng., Colorado State Univ., Fort Collins, CO.

IEEE Transactions on Neural Networks
|January 1, 1993
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

Neural network decision directed edge-adaptive Kalman filter for image estimation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

A least-squares-based 2-D filtering scheme for stereo image compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008
Same author

Detection of mines and minelike targets using principal component and neural-network methods.

IEEE transactions on neural networks·2008
Same author

A study of cloud classification with neural networks using spectral and textural features.

IEEE transactions on neural networks·2008
Same author

Errata to "A study of cloud classification with neural networks using spectral and textural features".

IEEE transactions on neural networks·2008
Same author

Underwater target classification using wavelet packets and neural networks.

IEEE transactions on neural networks·2008
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 a new method for training multilayer neural networks, enabling simultaneous weight adaptation and dynamic node creation. This approach optimizes network topology by minimizing mean-squared error for improved performance on complex tasks.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Multilayer backpropagation neural networks require efficient training methods.
  • Dynamic adjustment of network topology, including node creation, is crucial for optimal performance.
  • Existing methods may not efficiently handle simultaneous weight adaptation and node creation.

Purpose of the Study:

  • To present a novel approach for simultaneous recursive weight adaptation and node creation in multilayer backpropagation neural networks.
  • To develop a method that optimizes network topology by minimizing mean-squared error.
  • To demonstrate the algorithm's effectiveness on benchmark and real-world problems.

Main Methods:

  • Utilized time and order update formulations within the orthogonal projection method.

Related Experiment Videos

  • Derived a recursive weight updating procedure for neural network training.
  • Developed a recursive node creation algorithm for weight adjustment during training.

    • Main Results:

    • The proposed approach enables optimal dynamic node creation, minimizing mean-squared error for each new topology.
    • Demonstrated effectiveness on benchmark problems like the multiplexer and decoder.
    • Successfully applied the algorithm to detect and classify buried dielectric anomalies using microwave sensor data.

    Conclusions:

    • The novel method provides an effective way to train neural networks with dynamic topology adjustments.
    • The approach achieves optimal node creation, leading to improved network performance.
    • The algorithm shows promise for both theoretical problems and practical applications in sensor data analysis.