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

Contextual processing of structured data by recursive cascade correlation.

Alessio Micheli1, Diego Sona, Alessandro Sperduti

  • 1Computer Science Department, University of Pisa, 56127 Pisa, Italy. micheli@di.unipi.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

MolVE: An Open-Source Web Platform for Visualizing and Evaluating AI-Designed Molecules to Aid in Prioritization.

Journal of chemical information and modeling·2026
Same author

Green design in living and bedroom spaces: exploring environmental restorativeness and affective qualities of spaces.

Frontiers in psychology·2025
Same author

Germline-aware deep learning models and benchmarks for predicting antibody VH-VL pairing.

mAbs·2025
Same author

Enhancing antibody-antigen interaction prediction with atomic flexibility.

PLoS computational biology·2025
Same author

Linking dynamic connectivity states to cognitive decline and anatomical changes in Alzheimer's disease.

NeuroImage·2025
Same author

On the application of neural networks for structured domains to fMRI data.

Neural networks : the official journal of the International Neural Network Society·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 the contextual recursive cascade correlation (CRCC) model, a novel approach for handling contextual information in structured domains using recursive neural networks. CRCC enhances prediction tasks by incorporating contextual data, outperforming the traditional recursive cascade correlation (RCC) model.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Chemistry

Background:

  • Recursive neural networks are effective for structured data.
  • Existing models like Recursive Cascade Correlation (RCC) often assume causality.
  • Contextual information is crucial for complex prediction tasks.

Purpose of the Study:

  • To propose a novel model, Contextual Recursive Cascade Correlation (CRCC), for structured domains.
  • To address the limitations of causality assumptions in existing models.
  • To enhance prediction accuracy by incorporating contextual information.

Main Methods:

  • Developed the Contextual Recursive Cascade Correlation (CRCC) model, a generalization of RCC.
  • Utilized frozen units to store and exploit contextual information.

Related Experiment Videos

  • Formally characterized CRCC's computational properties.

    • Main Results:

    • CRCC can compute contextual and causal supersource transductions, which RCC cannot.
    • Experimental results demonstrated CRCC's efficiency and efficacy on both controlled and real-world tasks.
    • CRCC showed superiority over RCC in tasks where structural causality is uncertain.

    Conclusions:

    • CRCC offers a significant advancement in handling contextual information in structured domains.
    • The model effectively overcomes the limitations of strict causality assumptions.
    • CRCC demonstrates superior performance in complex prediction tasks, including those in chemical structures.