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

Self-organizing network for optimum supervised learning.

M F Tenorio1, W T Lee

  • 1Sch. of Electr. Eng., Purdue Univ., West Lafayette, IN.

IEEE Transactions on Neural Networks
|January 1, 1990
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

Squamous Cell Carcinoma DNA Detection Using Ultrabright SERS Nanorattles and Magnetic Beads for Head and Neck Cancer Molecular Diagnostics.

Analytical methods : advancing methods and applications·2023
Same author

A Southeast Asian collaborative Delphi consensus on surveying risk factors for head and neck cancer screening and prevention.

Global surgery (London)·2022
Same author

Cystic prostatic carcinoma: case report and literature review.

Hong Kong medical journal = Xianggang yi xue za zhi·2020
Same author

Author Correction: Rapid Nanophotonics Assay for Head and Neck Cancer Diagnosis.

Scientific reports·2018
Same author

Rapid Nanophotonics Assay for Head and Neck Cancer Diagnosis.

Scientific reports·2018
Same author

Probing the magnetic profile of diluted magnetic semiconductors using polarized neutron reflectivity.

Scientific reports·2017
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 self-organizing neural network (SONN) algorithm outperforms backpropagation for chaotic time series identification. SONN creates simpler, more accurate models with less data and training time.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • System identification is crucial for understanding complex dynamic systems.
  • Traditional algorithms like backpropagation face challenges with chaotic time series.
  • Neural network architecture and parameter optimization are key research areas.

Purpose of the Study:

  • Introduce a new algorithm, the self-organizing neural network (SONN).
  • Evaluate SONN's effectiveness in system identification, specifically for chaotic time series.
  • Compare SONN's performance against the established backpropagation algorithm.

Main Methods:

  • The self-organizing neural network (SONN) algorithm was developed.
  • SONN automatically constructs network architecture, selects node functions, and adjusts weights.

Related Experiment Videos

  • Performance was benchmarked against backpropagation using chaotic time series identification.

    • Main Results:

    • SONN successfully identified chaotic time series.
    • SONN-generated models were simpler and more accurate than those from backpropagation.
    • SONN required significantly less training data and fewer training epochs.
    • The algorithm demonstrated potential as a classifier.

    Conclusions:

    • The self-organizing neural network (SONN) offers an efficient and effective approach to system identification.
    • SONN presents advantages over backpropagation in terms of model complexity, accuracy, and data efficiency.
    • SONN's capabilities extend to classification tasks, highlighting its versatility.