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 Video

Updated: Jul 7, 2026

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Neural network design using Voronoi diagrams.

N K Bose1, A K Garga

  • 1Dept. of Electr. and Comput. Eng., Pennsylvania State Univ., University Park, PA.

IEEE Transactions on Neural Networks
|January 1, 1993
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Vector Algebra: Graphical Method01:10

Vector Algebra: Graphical Method

Vectors can be multiplied by scalars, added to other vectors, or subtracted from other vectors. The vector sum of two (or more) vectors is called the resultant vector or, for short, the resultant.
We use the laws of geometry to construct resultant vectors, followed by trigonometry to find vector magnitudes and directions. For a geometric construction of the sum of two vectors in a plane, we follow the parallelogram rule. Suppose two vectors are at arbitrary positions. Translate either one of...
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
Neural Circuits01:25

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Network Function of a Circuit01:25

Network Function of a Circuit

Frequency response analysis in electrical circuits provides vital insights into a circuit's behavior as the frequency of the input signal changes. The transfer function, a mathematical tool, is instrumental in understanding this behavior. It defines the relationship between phasor output and input and comes in four types: voltage gain, current gain, transfer impedance, and transfer admittance. The critical components of the transfer function are the poles and zeros.
Neuron Structure01:30

Neuron Structure

Neurons are the main type of cell in the nervous system that generate and transmit electrochemical signals. They primarily communicate with each other using neurotransmitters at specific junctions called synapses. Neurons come in many shapes that often relate to their function, but most share three main structures: an axon and dendrites that extend out from a cell body.
Structure and Function of Neurons
The neuronal cell body—the soma— houses the nucleus and organelles vital to cellular...
Neuron Structure01:31

Neuron Structure

Overview

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Vector quantization of neural networks.

IEEE transactions on neural networks·2008
Same author

High resolution image formation from low resolution frames using Delaunay triangulation.

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

Superresolution and noise filtering using moving least squares.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2006
Same author

Landmine detection and classification with complex-valued hybrid neural network using scattering parameters dataset.

IEEE transactions on neural networks·2005
Same author

Molecular cloning of Clostridium difficile toxin A gene fragment in lambda gt11.

FEBS letters·1987
Same author

On the trail of the wolf-children.

Genetic psychology monographs·1959
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 designing neural networks to classify complex data patterns. It utilizes Voronoi diagrams to determine network structure and connection weights for improved pattern recognition.

Area of Science:

  • Computational intelligence
  • Machine learning
  • Pattern recognition

Background:

  • Multilayer feedforward neural networks are widely used for pattern classification.
  • Determining optimal network architecture (layers, neurons) and connection weights remains a challenge.
  • Existing methods may not fully exploit the geometric properties of feature spaces.

Purpose of the Study:

  • To propose a novel, geometry-based approach for designing neural networks.
  • To determine the optimal number of layers, neurons per layer, and connection weights.
  • To enhance pattern classification capabilities in multidimensional feature spaces.

Main Methods:

  • Construction of a Voronoi diagram over data points in the feature space.
  • Utilizing the Voronoi diagram to define neural network topology and parameters.

More Related Videos

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
10:44

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

Related Experiment Videos

Last Updated: Jul 7, 2026

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
10:44

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

  • Applying the method to a multilayer feedforward neural network for pattern classification.

    • Main Results:

    • The proposed approach successfully determines neural network architecture and connection weights.
    • The method leverages geometric properties of the feature space for effective classification.
    • Demonstrated usefulness in deriving alternative neural network structures.

    Conclusions:

    • The Voronoi diagram-based approach offers a novel and effective method for neural network design.
    • This technique enhances pattern classification in multidimensional spaces.
    • The approach provides flexibility in deriving diverse neural network structures for specific tasks.