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

Dynamic topology representing networks.

J Si1, S Lin, M A Vuong

  • 1Department of Electrical Engineering, Arizona State University, Tempe 85287, USA. si@asu.edu

Neural Networks : the Official Journal of the International Neural Network Society
|September 15, 2000
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

Association of Computed Tomography Radiomics Signature with Progression-free Survival in Neuroblastoma Patients.

Clinical oncology (Royal College of Radiologists (Great Britain))·2023
Same author

Integrated analysis of whole genome and transcriptome sequencing reveals a frameshift mutation associated with recessive embryonic lethality in Holstein cattle.

Animal genetics·2021
Same author

Caspofungin combined with TMP/SMZ as a first-line therapy for moderate-to-severe PCP in patients with human immunodeficiency virus infection.

HIV medicine·2020
Same author

[A single-center retrospective study on axillary evaluation in 1 557 breast ductal carcinoma in situ patients between 2006 and 2016].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2019
Same author

Ten-day bismuth-containing quadruple therapy is effective as first-line therapy for Helicobacter pylori-related chronic gastritis: a prospective randomized study in China.

Clinical microbiology and infection : the official publication of the European Society of Clinical Microbiology and Infectious Diseases·2017
Same author

Ras-association domain family 10 acts as a novel tumor suppressor through modulating MMP2 in hepatocarcinoma.

Oncogenesis·2016
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

We introduce Dynamic Topology Representing Networks (DTRN), an algorithm that learns data topology and clustering. DTRN adaptively adjusts its structure for improved learning speed and classification accuracy.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Data Mining

Background:

  • Traditional clustering and topology learning methods often require pre-defined structures or struggle with dynamic data.
  • Adaptive network architectures are crucial for handling complex, evolving datasets.

Purpose of the Study:

  • To propose a novel algorithm, Dynamic Topology Representing Networks (DTRN), for simultaneous topology and clustering information learning.
  • To enhance adaptive network models by introducing dynamic node growth and deletion mechanisms.

Main Methods:

  • DTRN employs a vigilance test for adaptive node growth and a winner-take-quota strategy with annealing for clustering.
  • A competitive Hebbian rule is utilized for concurrent learning of global topology and clustering.
  • Learned topology information dynamically informs node deletion and the annealing process.

Related Experiment Videos

Main Results:

  • The DTRN algorithm demonstrates effectiveness in preserving data topology.
  • Simulations show competitive or superior learning speed compared to existing algorithms.
  • The algorithm performs well in classification tasks, outperforming comparable methods.

Conclusions:

  • DTRN offers an effective approach for learning topology and clustering from data.
  • The adaptive nature of DTRN allows for efficient processing of complex datasets.
  • The algorithm shows promise for various machine learning applications requiring topology preservation and accurate classification.