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

Encoding strategy for maximum noise tolerance bidirectional associative memory.

Dan Shen1, Jose B Cruz

  • 1Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH 43210, USA. shen.100@osu.edu

IEEE Transactions on Neural Networks
|March 25, 2005
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

Report of a case of renal hilum Castleman disease complicated with Paget's disease of the breast.

Frontiers in medicine·2026
Same author

Pathogen spectrum of pulmonary infections in kidney transplant recipients and the diagnostic value of mNGS: a sputum and BALF study based on clinical decision-making.

Frontiers in cellular and infection microbiology·2026
Same author

Intratracheal Lactobacillus rhamnosus attenuates poultry-house PM<sub>2.5</sub>-induced lung inflammation in broilers by remodeling the pulmonary microbiota-metabolite axis.

Environmental pollution (Barking, Essex : 1987)·2026
Same author

Moderate and Severe Exacerbations and Healthcare Resource Utilization in Chinese Patients with COPD on Triple Therapy: A Retrospective Database Study.

Advances in therapy·2026
Same author

Bioinspired adhesive hydrogel incorporated with PDA@CuMOF for infected wound therapy.

Colloids and surfaces. B, Biointerfaces·2026
Same author

Lung microbiota-mediated biotransformation of mogroside preserves pulmonary barrier integrity and attenuates PM<sub>2.5</sub>-induced inflammation via NF-κB-Th17 modulations.

NPJ biofilms and microbiomes·2026
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 optimizes bidirectional associative memory (BAM) using a genetic algorithm to maximize noise tolerance. The enhanced BAM reliably recalls correct patterns within a larger tolerance set, improving fault tolerance.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • Bidirectional Associative Memory (BAM) is a type of recurrent artificial neural network.
  • Standard BAM models can be sensitive to noisy input patterns.
  • Improving noise tolerance is crucial for robust pattern recognition.

Purpose of the Study:

  • To extend the basic BAM model by optimizing weights for maximum noise tolerance.
  • To develop an optimized BAM that enhances error correction and fault tolerance properties.
  • To define and achieve the largest possible noise tolerance set for BAM.

Main Methods:

  • Weight selection in the correlation matrix for a given set of training pairs.
  • Mathematical proof to establish the properties of the maximum noise tolerance set.

Related Experiment Videos

  • Utilizing a standard genetic algorithm (GA) to calculate optimal weights.
  • Computer simulations to validate the enhanced BAM's performance.

    • Main Results:

    • The optimized BAM achieves a maximum noise tolerance set, defined as the union of maximum basins of attraction.
    • The optimized BAM correctly recalls training pairs even with noisy inputs within the tolerance set.
    • Patterns outside the maximum tolerance set by one Hamming distance do not converge to the correct training pair, demonstrating improved specificity.

    Conclusions:

    • The proposed weight optimization significantly enhances the noise and fault tolerance of BAM networks.
    • The genetic algorithm effectively identifies weights that maximize the tolerance set.
    • This optimized BAM offers improved reliability for pattern recognition tasks in the presence of noise.