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

Abductive reasoning with recurrent neural networks.

Ashraf M Abdelbar1, Emad A M Andrews, Donald C Wunsch

  • 1Department of Computer Science, American University in Cairo, 113 Kasr El Aini Street, Cairo, Egypt. abdelbar@aucegypt.edu

Neural Networks : the Official Journal of the International Neural Network Society
|July 10, 2003
PubMed
Summary

This study introduces a novel method to reduce neural network size for cost-based abduction (CBA) proofs. This advancement offers a more efficient approach to finding the best explanations for observed data in AI reasoning.

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

Current state of the art of new prostate MRI technologies and potential future developments.

BJR open·2026
Same author

Prostate Cancer: Current Status of Novel Molecular Imaging and Future Prospects.

European urology focus·2025
Same author

DeepART: Deep gradient-free local learning with adaptive resonance.

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

Adaptive Nussbaum Design for Nonholonomic Systems With Asymptotic Stabilization Against False Data Injection.

IEEE transactions on cybernetics·2025
Same author

The visualization of Orphadata neurology phenotypes.

Frontiers in digital health·2023
Same author

Subtypes of relapsing-remitting multiple sclerosis identified by network analysis.

Frontiers in digital health·2023

Area of Science:

  • Artificial Intelligence
  • Computational Logic
  • Cognitive Science

Background:

  • Abduction is a reasoning process used to infer the best explanation for observed data.
  • Cost-based abduction (CBA) formalizes this by assigning costs to assumptions needed for explanations.
  • Previous work utilized high-order recurrent networks for finding least-cost CBA proofs.

Purpose of the Study:

  • To present a novel method for significantly reducing the size of neural networks used in CBA.
  • To improve the efficiency of generating explanations for given evidence.

Main Methods:

  • Development of a new technique to construct smaller neural networks for CBA instances.
  • Implementation and testing of the proposed method.

Related Experiment Videos

Main Results:

  • The new method demonstrably reduces the size of the generated neural network compared to prior approaches.
  • Experimental results show the performance of the optimized network.

Conclusions:

  • The presented method offers a more computationally efficient solution for cost-based abduction.
  • This work contributes to more scalable and practical AI reasoning systems.