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

Parallel, self-organizing, hierarchical neural networks.

O K Ersoy1, D Hong

  • 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

The impact of preoperative stoma education on postoperative outcomes for patients with new stomas after colorectal surgery: a systematic review and meta-analysis.

Techniques in coloproctology·2025
Same author

Canadian Surgery Forum: Abstracts of presentations to the Annual Meetings of the Canadian Association of Bariatric Physicians and Surgeons, Canadian Association of General Surgeons, Canadian Association of Thoracic Surgeons, Canadian Hepato-Pancreato-Biliary Association, Canadian Society of Surgical Oncology, Canadian Society of Colon and Rectal Surgeons, Vancouver, BC, Sept. 17-21, 2013.

Canadian journal of surgery. Journal canadien de chirurgie·2025
Same author

Starting position during colonoscopy: a systematic review and meta-analysis of randomized controlled trials.

Techniques in coloproctology·2024
Same author

The modified frailty index predicts postoperative morbidity in elective hernia repair patients: analysis of the national inpatient sample 2015-2019.

Hernia : the journal of hernias and abdominal wall surgery·2024
Same author

Cutting seton for the treatment of cryptoglandular fistula-in-ano: a systematic review and meta-analysis.

Techniques in coloproctology·2023
Same author

Prognostic value of cardiac magnetic resonance imaging feature tracking technology in patients with light chain amyloidosis.

Clinical radiology·2023
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 parallel, self-organizing, hierarchical neural network (PSHNN) offers improved classification accuracy and efficiency. This advanced architecture outperforms traditional multilayered networks, demonstrating superior performance in experiments.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Existing neural network architectures face challenges in complexity and efficiency.
  • Multilayered networks with back-propagation training have limitations in parallel processing.

Purpose of the Study:

  • To introduce a new neural network architecture: the parallel, self-organizing, hierarchical neural network (PSHNN).
  • To evaluate the performance and advantages of the PSHNN compared to existing models.

Main Methods:

  • The PSHNN architecture consists of multiple stages, each a self-contained neural network (SNN).
  • Error detection and nonlinear transformation are applied between stages for rejected input vectors.
  • A truly parallel architecture allows simultaneous operation of all stages during testing.

Related Experiment Videos

Main Results:

  • The PSHNN demonstrates optimized system complexity by minimizing the number of self-organizing stages.
  • Experiments show high classification accuracy and minimized learning and recall times.
  • The PSHNN architecture exhibits superior performance compared to multilayered networks with back-propagation training.

Conclusions:

  • The PSHNN represents a significant advancement in neural network design.
  • Its parallel and self-organizing nature leads to enhanced efficiency and accuracy.
  • The PSHNN architecture is a promising alternative for complex classification tasks.