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 nondeterministic fuzzy tree automata into recursive neural networks.

Marco Gori1, Alfredo Petrosino

  • 1Dipartimento di Ingegneria dell'Informazione, Università di Siena, 53100 Siena, Italy. marco@dii.unisi.it

IEEE Transactions on Neural Networks
|November 30, 2004
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

Artificial intelligence in medicine: a position paper by the Italian Society of Internal Medicine.

Internal and emergency medicine·2025
Same author

A systematic literature review of spatio-temporal graph neural network models for time series forecasting and classification.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Interoperable Traceability in Agrifood Supply Chains: Enhancing Transport Systems Through IoT Sensor Data, Blockchain, and DataSpace.

Sensors (Basel, Switzerland)·2025
Same author

State-space modeling in long sequence processing: a survey on recurrence in the transformer era.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Continual learning of conjugated visual representations through higher-order motion flows.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Investigation and management of resistant hypertension: British and Irish Hypertension Society position statement.

Journal of human hypertension·2024
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 fuzzy neural systems capable of handling structured information by integrating prior knowledge and learning unknown rules from data. Recursive neural networks are used to represent fuzzy tree automata, enhancing symbolic processing capabilities.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Fuzzy Systems

Background:

  • Fuzzy neural systems facilitate symbolic and subsymbolic information exchange.
  • Existing models struggle with structured information crucial for symbolic processing.
  • Patterns often possess structure and fuzziness at the primitive level.

Purpose of the Study:

  • To demonstrate how recursive neural networks can represent nondeterministic fuzzy frontier-to-root tree automata.
  • To integrate prior knowledge via fuzzy state transition rules into recursive networks.
  • To enable data-driven learning for unknown rules within these systems.

Main Methods:

  • Utilizing recursive neural networks for structured information representation.
  • Injecting fuzzy state transition rules as prior knowledge.

Related Experiment Videos

  • Employing data-driven learning to infer unknown rules.

    • Main Results:

    • Recursive neural networks successfully represent fuzzy tree automata.
    • A stable encoding algorithm is proven for fuzzy finite-state dynamics injection.
    • The approach combines symbolic knowledge with data-driven learning.

    Conclusions:

    • Recursive neural networks offer a robust framework for fuzzy structured information processing.
    • This method enhances the capabilities of fuzzy neural systems for complex applications.
    • The stability of the learning and encoding process is mathematically established.