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

A neural network approach to a Bayesian statistical decision problem.

S Miyake1, F Kanaya

  • 1NTT Transmission Syst. Lab., Kanagawa.

IEEE Transactions on Neural Networks
|January 1, 1991
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

Precision Spectral Measurements of Chromium and Titanium from 10 to 250  GeV/n and Sub-Iron to Iron Ratio with the Calorimetric Electron Telescope on the International Space Station.

Physical review letters·2025
Same author

Direct Measurement of the Spectral Structure of Cosmic-Ray Electrons+Positrons in the TeV Region with CALET on the International Space Station.

Physical review letters·2023
Same author

Erratum: Charge-Sign Dependent Cosmic-Ray Modulation Observed with the Calorimetric Electron Telescope on the International Space Station [Phys. Rev. Lett. 130, 211001 (2023)].

Physical review letters·2023
Same author

Charge-Sign Dependent Cosmic-Ray Modulation Observed with the Calorimetric Electron Telescope on the International Space Station.

Physical review letters·2023
Same author

Direct Measurement of the Cosmic-Ray Helium Spectrum from 40 GeV to 250 TeV with the Calorimetric Electron Telescope on the International Space Station.

Physical review letters·2023
Same author

Cosmic-Ray Boron Flux Measured from 8.4  GeV/n to 3.8  TeV/n with the Calorimetric Electron Telescope on the International Space Station.

Physical review letters·2023
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

New objective functions called Generalized Mean-Squared Error (GMSE) can optimize neural networks for statistical decision problems with any loss function, offering a Bayes optimal solution.

Area of Science:

  • Machine Learning
  • Statistical Decision Theory
  • Artificial Intelligence

Background:

  • Statistical decision problems involve making optimal choices under uncertainty.
  • Neural networks are powerful tools for complex data analysis.
  • Generic loss functions are essential for defining problem-specific optimality criteria.

Purpose of the Study:

  • To introduce Generalized Mean-Squared Error (GMSE) objective functions.
  • To enable neural networks to find Bayes optimal solutions for generic loss functions.
  • To enhance the applicability of neural networks in statistical decision theory.

Main Methods:

  • Development of novel GMSE objective functions.
  • Integration of GMSE into neural network architectures.

Related Experiment Videos

  • Theoretical analysis of GMSE for Bayes optimality.

    • Main Results:

    • GMSE objective functions provide a unified framework for optimization.
    • Neural networks utilizing GMSE achieve Bayes optimal performance.
    • The proposed method is applicable to a wide range of statistical decision problems.

    Conclusions:

    • GMSE objective functions represent a significant advancement in neural network optimization.
    • This approach broadens the utility of neural networks in statistical decision making.
    • The findings pave the way for more robust and adaptable AI systems.