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

HYCONES: a hybrid connectionist expert system

B de F Leão1, E B Reátegui

  • 1Institute of Cardiology RS, Porto Alegre, Brazil.

Proceedings. Symposium on Computer Applications in Medical Care
|January 1, 1993
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

The software challenge for the next decade: the global objects scenario.

Studies in health technology and informatics·1999
Same author

Combining a neural network with case-based reasoning in a diagnostic system.

Artificial intelligence in medicine·1997
Same author

Hycones: a hybrid approach to designing decision support systems.

M.D. computing : computers in medical practice·1996
Same author

Enhancing medical database semantics.

Proceedings. Symposium on Computer Applications in Medical Care·1995
Same author

Hybrid systems: a promising solution for better decision support tools.

Medinfo. MEDINFO·1995
Same author

HYCONES II: a tool to build hybrid connectionist expert systems.

Proceedings. Symposium on Computer Applications in Medical Care·1994
Same journal

Intelligent monitor for an anesthesia breathing circuit.

Proceedings. Symposium on Computer Applications in Medical Care·1995
Same journal

Design considerations for intelligent data entry: development of MedIO.

Proceedings. Symposium on Computer Applications in Medical Care·1995
Same journal

Medical information retrieval and WWW browsers at Mayo.

Proceedings. Symposium on Computer Applications in Medical Care·1995
Same journal

A model of clinical query management that supports integration of biomedical information over the World Wide Web.

Proceedings. Symposium on Computer Applications in Medical Care·1995
Same journal

Automated MeSH indexing of the World-Wide Web.

Proceedings. Symposium on Computer Applications in Medical Care·1995
Same journal

Teaching literature searching in the context of the World Wide Web.

Proceedings. Symposium on Computer Applications in Medical Care·1995
See all related articles

This study introduces HYCONES, a hybrid expert system combining neural networks and symbolic AI for enhanced learning and knowledge representation. The system demonstrates effective knowledge acquisition and initial validation.

Area of Science:

  • Artificial Intelligence
  • Computer Science

Background:

  • Expert systems traditionally rely on symbolic knowledge representation.
  • Neural networks offer powerful learning capabilities but often lack explicit knowledge structures.
  • Integrating these approaches can overcome individual limitations.

Purpose of the Study:

  • To introduce HYCONES, a Hybrid Connectionist Expert System.
  • To detail the integration of neural networks and symbolic frames.
  • To present the system's architecture, knowledge base, and knowledge acquisition methods.

Main Methods:

  • Developed a tightly-coupled hybrid system (HYCONES).
  • Integrated a symbolic paradigm (frames) with a connectionist approach (neural networks).
  • Implemented an automatic knowledge acquisition technique from a case database.

Related Experiment Videos

Main Results:

  • The HYCONES architecture successfully combines symbolic knowledge representation with neural network learning.
  • The system features a hybrid knowledge base and an automatic knowledge acquisition method.
  • Initial validation of the HYCONES system has been performed.

Conclusions:

  • Hybrid systems like HYCONES offer a promising direction for AI by leveraging the strengths of both symbolic and connectionist methods.
  • The presented knowledge acquisition technique is effective for populating the hybrid knowledge base.
  • Further research and development are planned for advanced applications.