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

Morphological bidirectional associative memories.

G X. Ritter1, J L. Diaz-de-Leon, P Sussner

  • 1Department of Computer and Information Science and Engineering, University of Florida, CSE Building, Gainesville, FL, USA

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 2003
PubMed
Summary
This summary is machine-generated.

This study introduces morphological neural networks, replacing traditional multiplication and addition with addition and maximum operations. These novel networks exhibit distinct properties and offer perfect bidirectional recall for corrupted patterns.

Related Experiment Videos

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 journal

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

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

New results on prescribed-time synchronization of complex networks via intermittent control.

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

Variance-constrained multi-view ensemble broad network for imbalanced data.

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

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

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

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

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

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

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

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Pattern Recognition

Background:

  • Traditional artificial neural networks rely on linear operations (multiplication and addition) followed by thresholding for nonlinearity.
  • This linear-sum-of-products approach is fundamental to many pattern recognition tasks.
  • Existing models have limitations in handling certain types of pattern complexities.

Purpose of the Study:

  • Introduce a novel class of artificial neural networks: morphological neural networks.
  • Explore the mathematical theory and properties of morphological bidirectional associative memories (MBAMs).
  • Demonstrate the advantages of morphological networks over traditional semilinear models.

Main Methods:

  • Replaced multiplication and addition with addition and maximum (or minimum) operations in network computation.
  • Developed a mathematical framework for morphological bidirectional associative memories (MBAMs).
  • Analyzed the nonlinear properties arising before thresholding in morphological networks.

Main Results:

  • Morphological neural networks exhibit nonlinear computation before thresholding due to the max-of-sums operation.
  • Established theoretical conditions guaranteeing perfect bidirectional recall for corrupted patterns in MBAMs.
  • Illustrated performance differences highlighting the advantages of the morphological model.

Conclusions:

  • Morphological neural networks offer a fundamentally different computational paradigm compared to traditional models.
  • MBAMs provide robust pattern recall capabilities, even for noisy or incomplete data.
  • The novel approach opens new avenues for advanced pattern recognition and associative memory research.