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

TMLNN: triple-valued or multiple-valued logic neural network.

G Wang1, H Shi

  • 1Department of Computer at Chongqing University of Posts and Telecommunications, Chongqing, China.

IEEE Transactions on Neural Networks
|February 8, 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

Interaction in vivo and in vitro of the metastasis-inducing S100 protein, S100A4 (p9Ka) with S100A1.

The Journal of biological chemistry·2001
Same author

Hyperactive tendon reflexes in spastic multiple sclerosis: measures and mechanisms of action.

Archives of physical medicine and rehabilitation·2000
Same author

Synthesis of unsaturated carboacyclic nucleoside analogues via Mitsunobu reactions.

Nucleosides, nucleotides & nucleic acids·2000
Same author

Synthesis and cytokine modulation properties of pyrrolo[2, 3-d]-4-pyrimidone nucleosides.

Journal of medicinal chemistry·2000
Same author

Reciprocal information flow between prefrontal cortex and ventral tegmental area in an animal model of schizophrenia.

Neuroreport·2000
Same author

The "waiting period" of sensory and motor axons in early chick hindlimb: its role in axon pathfinding and neuronal maturation.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2000
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 paper introduces a novel neuron model for processing multi-valued logic. The triple-valued or multiple-valued logic neuron (TMLN) enables neural networks to represent and process complex logic rules efficiently.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Logic Systems

Background:

  • Traditional neural networks primarily handle binary logic.
  • Representing and processing multi-valued logic within neural networks presents significant challenges.
  • Existing methods lack the flexibility to directly encode multi-valued logic rules.

Purpose of the Study:

  • To propose a novel neuron model capable of representing triple-valued or multiple-valued logic.
  • To demonstrate the efficacy of this model in constructing neural networks for multi-valued logic inference.
  • To facilitate the extraction of logic rules from trained neural networks.

Main Methods:

  • Introduction of the triple-valued or multiple-valued logic neuron (TMLN) model.

Related Experiment Videos

  • Development of TMLN-AND and TMLN-OR neurons for "logic and" and "logic or" operations.
  • Construction of a multiple-layer neural network (TMLNN) using TMLNs.
  • Presentation of a convergent training algorithm for TMLNN.

    • Main Results:

    • TMLN effectively represents individual triple-valued or multiple-valued logic rules.
    • TMLNNs can implement complete triple-valued or multiple-valued logic inference systems.
    • Logic rules are easily extractable from the trained TMLNN architecture.

    Conclusions:

    • The TMLN model provides a robust framework for neural network-based multi-valued logic representation.
    • TMLNNs offer a powerful tool for knowledge representation and reasoning in artificial intelligence.
    • This approach simplifies the integration of symbolic logic processing within neural architectures.