Jove
Visualize
Contact Us

Related Experiment Videos

Lattice algebra approach to single-neuron computation.

G X Ritter1, G Urcid

  • 1CISE Dept., Univ. of Florida, Gainesville, FL, USA.

IEEE Transactions on Neural Networks
|February 2, 2008
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

Rank-based decompositions of morphological templates.

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

Morphological associative memories.

IEEE transactions on neural networks·2008
Same author

A new parallel binary image shrinking algorithm.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·1995
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
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

This study introduces a new mathematical model for dendritic computation in neurons, enhancing artificial neural networks. This morphological perceptron model demonstrates powerful approximation capabilities for complex data.

Area of Science:

  • Computational neuroscience
  • Artificial intelligence
  • Mathematical modeling

Background:

  • Dendritic structures in neurons are increasingly recognized as crucial computational units.
  • Traditional artificial neural network models often oversimplify neuron structure, neglecting dendritic complexity.
  • Advances in biophysics and neurocomputing highlight the need for more realistic neuron models.

Purpose of the Study:

  • To introduce and develop a mathematical model for dendrite computation in morphological neurons.
  • To establish a novel paradigm in artificial neural networks by incorporating realistic dendritic processes.
  • To demonstrate the computational capabilities of this enriched neuron model.

Main Methods:

  • Development of a mathematical model for dendrite computation based on lattice algebra.

Related Experiment Videos

  • Analysis of computational capabilities using illustrative examples.
  • Theoretical proof of approximation capabilities for single-layer morphological perceptrons.

    • Main Results:

    • The proposed morphological neuron model, incorporating dendrites, exhibits significant computational power.
    • Any single-layer morphological perceptron can approximate compact regions in Euclidean space with high accuracy.
    • A training algorithm for these perceptrons was developed and tested on nonlinear problems.

    Conclusions:

    • The mathematical model provides a more realistic and powerful approach to artificial neural networks.
    • Dendritic computation is essential for advanced logical operations within neurons and artificial systems.
    • The developed model and training algorithm show promise for solving complex nonlinear problems.