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

Data qualification: logic analysis applied toward neural network training

B P Bergeron1, R S Shiffman, R L Rouse

  • 1Harvard Medical School Decision Systems Group, Department of Radiology, Brigham & Women's Hospital, Boston, MA 02115.

Computers in Biology and Medicine
|March 1, 1994
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

Incomplete lung recovery following sub-acute inhalation of combustion-derived ultrafine particles in mice.

Particle and fibre toxicology·2016
Same author

The wireless Web and patient care.

The Journal of medical practice management : MPM·2001
Same author

Is it safe? Security speed bumps on the information highway.

The Journal of medical practice management : MPM·2001
Same author

Reducing clip-on clutter. The pros and cons of multipurpose communications tools.

Postgraduate medicine·2001
Same author

Voice recognition in clinical medicine: process versus technology.

The Journal of medical practice management : MPM·2001
Same author

Pen-based computing: applications in clinical medicine.

The Journal of medical practice management : MPM·2001
Same journal

Corrigendum to "Integrating experimental biology, computational methods, and artificial Intelligence in anticancer drug discovery: Bridging the translational Gap" [Comput. Biol. Med. 213 (2026) 111832].

Computers in biology and medicine·2026
Same journal

Organ dose optimization for a point-of-care forearm X-ray photon-counting CT.

Computers in biology and medicine·2026
Same journal

Physics-guided transformation of breathomic feature spaces into disease-specific representations for respiratory disease classification.

Computers in biology and medicine·2026
Same journal

An AI-driven deep learning pipeline for taxonomic classification and biodiversity assessment of deep-sea environmental DNA.

Computers in biology and medicine·2026
Same journal

Rapid personalisation of cardiovascular models using invasively measured right ventricular pressure.

Computers in biology and medicine·2026
Same journal

Biologically inspired mechanisms for enhancing robustness in EEG signal modeling: Challenges, opportunities, and perspectives.

Computers in biology and medicine·2026
See all related articles

Controlling noise in training data is crucial for neural network performance. Decision tables offer a practical, domain-independent method to optimize training data by removing noise and evaluating network training.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Data Science

Background:

  • Neural networks require high-quality training data for effective pattern mapping.
  • Manual validation of large datasets is often impractical and time-consuming.
  • Noise in training data can hinder the development of accurate internal representations.

Purpose of the Study:

  • To investigate the use of decision table techniques for optimizing neural network training datasets.
  • To provide a practical and domain-independent method for data preprocessing.
  • To explore decision tables as a tool for both filtering training data and evaluating neural network performance.

Main Methods:

  • Utilized decision table techniques to process and refine training set data.

Related Experiment Videos

  • Implemented mechanisms within decision tables to identify and remove ambiguity and contradictions.
  • Applied decision tables as a data filtering mechanism prior to neural network training.
  • Employed decision tables for the evaluation of neural network training processes.

    • Main Results:

    • Decision tables effectively processed training data to mitigate noise.
    • The techniques demonstrated domain independence, applicable across various data types.
    • Ambiguities and contradictions within the training set were successfully identified and resolved.
    • Decision tables proved useful in evaluating the outcomes of neural network training.

    Conclusions:

    • Decision table techniques offer a robust and practical solution for optimizing neural network training data.
    • These methods provide a domain-independent approach to data cleaning and validation.
    • The application of decision tables can lead to improved neural network performance by ensuring data quality.