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

Mimic nets.

G E Johnson1

  • 1Anal. Sci. Corp., Reston, VA.

IEEE Transactions on Neural Networks
|January 1, 1993
PubMed
Summary
This summary is machine-generated.

This study presents mimic nets, a computational technique for automated ranking and classification. These artificial neural networks precisely learn from training data for accurate recall and sensible extrapolation.

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 in vitro alkaline comet assay with liver models as a complementary tool for genotoxicity assessment of N-nitrosamines.

Archives of toxicology·2026
Same author

The Condition of the Teeth of Children in Public Schools.

International dental journal (Philadelphia, Pa.)·2023
Same author

Understanding the importance of low-molecular weight (ethylene oxide- and propylene oxide-induced) DNA adducts and mutations in risk assessment: Insights from 15 years of research and collaborative discussions.

Environmental and molecular mutagenesis·2018
Same author

Derivation of point of departure (PoD) estimates in genetic toxicology studies and their potential applications in risk assessment.

Environmental and molecular mutagenesis·2014
Same author

TNFα from classically activated macrophages accentuates epithelial to mesenchymal transition in obliterative bronchiolitis.

American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons·2013
Same author

Diagnostic correlation between the expression of the DNA repair enzyme N-methylpurine DNA glycosylase and esophageal adenocarcinoma onset: a retrospective pilot study.

Diseases of the esophagus : official journal of the International Society for Diseases of the Esophagus·2012
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

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Automated ranking and classification are crucial tasks in data analysis.
  • Existing methods may lack precision or struggle with data extrapolation.
  • Feedforward neural networks offer a potential solution but require effective training techniques.

Purpose of the Study:

  • Introduce novel techniques, termed mimic nets, for training feedforward nets.
  • Enable automation of ranking and classification tasks.
  • Ensure precise data mimicry and reliable extrapolation capabilities.

Main Methods:

  • Utilized linear programming algorithms for net training.
  • Trained nets to exactly mimic expert performance on training data.

Related Experiment Videos

  • Adapted net structure (nodes, connections) and weights simultaneously.
  • Focused on noiseless training data and errorless recall.

    • Main Results:

    • Demonstrated the ability of mimic nets to precisely learn from self-consistent training data.
    • Identified efficacious features and assessed training data quality.
    • Showcased the capacity for sensible extrapolation beyond training examples.
    • Proved the existence of a mimic net for any consistent training dataset.

    Conclusions:

    • Mimic nets provide a computationally efficient and purposeful method for automated ranking and classification.
    • The technique ensures high fidelity to training data and reliable generalization.
    • Mimic nets are a valuable tool for problems demanding exact data recall and sensible extrapolation.