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

Circular nodes in neural networks

M J Kirby1, R Miranda

  • 1Department of Mathematics, Colorado State University, Fort Collins 80523 USA.

Neural Computation
|February 15, 1996
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

Origin of the high coercivity in FeNi inspired magnets.

Scientific reports·2026
Same author

Lanthanide-porphyrin species as Kondo irreversible switches through tip-induced coordination chemistry.

Nanoscale·2021
Same author

Evidence for a spin acoustic surface plasmon from inelastic atom scattering.

Scientific reports·2021
Same author

Health literacy and hypertension outcomes in a multi-ethnic population: the HELIUS study.

European journal of public health·2019
Same author

Discrete Electronic Subbands due to Bragg Scattering at Molecular Edges.

Physical review letters·2019
Same author

Graphene catalyzes the reversible formation of a C-C bond between two molecules.

Science advances·2018
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study introduces circular nodes for neural networks, enabling the representation of angular data. This innovation offers a novel approach for analyzing periodic phenomena and approximating functions, serving as an alternative to Fourier series.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Mathematics

Background:

  • Traditional neural networks use nodes transmitting real numbers, typically representing amplitudes.
  • Characterizing periodic phenomena often requires specialized techniques.

Purpose of the Study:

  • To introduce a novel circular node for neural networks capable of storing and transmitting angular information.
  • To develop propagation formulas and demonstrate applications for networks utilizing circular nodes.
  • To present circular nodes as an alternative to Fourier series for periodic function approximation.

Main Methods:

  • Development of forward and backward propagation formulas for circular node networks.
  • Application of circular nodes in constructing self-maps, periodic compression, and manifold decomposition.

Related Experiment Videos

  • Integration of circular nodes into a bottleneck network architecture for dynamic system encoding.

    • Main Results:

    • Demonstration of circular nodes' ability to handle angular data and periodic phenomena.
    • Successful application in constructing a homeomorphism between a trefoil knot and a unit circle.
    • Encoding of dynamic systems on limit cycles, exemplified by the Kuramoto-Sivashinsky equation.

    Conclusions:

    • Circular nodes offer a powerful new tool for neural networks, particularly for periodic data.
    • This approach provides a viable alternative to Fourier series decomposition for approximating periodic functions.
    • The framework facilitates the analysis and modeling of complex periodic systems.