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

A general framework for learning rules from data.

Bruno Apolloni1, Anna Esposito, Dario Malchiodi

  • 1Dipartimento di Scienze dell'Informazione, Università di Milano, 20135 Milano, Italy. apolloni@dsi.unimi.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

<i>N-</i>nonyloxypentyl-L-deoxynojirimycin reduces <i>Stenotrophomonas maltophilia</i> virulence <i>in vitro</i> and in <i>Galleria mellonella</i> infection model.

Frontiers in microbiology·2026
Same author

l-NBDNJ allosteric chaperone for multiple defective enzymes involved in lysosomal storage disorders (LSDs).

Bioorganic chemistry·2026
Same author

Health Beyond Disease: An Integrated Assessment of Quality of Life, Perceived Health, and Lifestyle Behaviours in a Peri-Urban Kenyan Population-A Pilot Study.

International journal of environmental research and public health·2026
Same author

Retrospective Analysis of a Quince, Olive Leaf, and Amaranth Nutraceutical in Patients with Metabolic Syndrome.

Medicina (Kaunas, Lithuania)·2025
Same author

Synthesis and preliminary biological evaluation of novel steroidal compounds as antibacterial agents.

Steroids·2025
Same author

Exploring the impact of noise, language familiarity, and experimental settings on emotion recognition.

Frontiers in psychology·2025
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 a two-phase approach for learning symbolic rules from data, combining neural networks and a PAC-like algorithm. It effectively discriminates emotional states by managing information and learning rules without prior knowledge.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Extracting understandable symbolic rules from sensory data is challenging.
  • Existing methods often lack flexibility in rule family selection or integration of neural and symbolic learning.
  • Information management is crucial for learning rules with limited prior knowledge.

Purpose of the Study:

  • To develop a novel computational learning paradigm for generating symbolic rules from sensory data.
  • To integrate a multilayer perceptron with a PAC-like algorithm for rule induction.
  • To address information management challenges in learning rules without a priori assumptions.

Main Methods:

  • A two-phase approach: 1) A multilayer perceptron maps features to propositional variables. 2) A PAC-like algorithm learns Boolean expressions on these variables.

Related Experiment Videos

  • The neural network is trained for class discrimination, producing Boolean outputs.
  • A feedback mechanism based on rule suitability evaluates and refines the learned rules.

    • Main Results:

    • The proposed procedure effectively learns symbolic rules from data.
    • It demonstrates successful formal discrimination among emotional states.
    • The method offers a comparison benchmark against existing symbolic and subsymbolic approaches.

    Conclusions:

    • The integrated neural and symbolic learning approach provides a robust framework for rule induction.
    • This method enhances information management for learning complex patterns.
    • It shows promise for applications requiring interpretable models, such as emotion recognition.