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

Temporal difference learning applied to sequential detection.

C Guo1, A Kuh

  • 1Dept. of Electr. Eng., Hawaii Univ., Honolulu, HI.

IEEE Transactions on Neural Networks
|January 1, 1997
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

Erratum: "Highly versatile, two-color setup for high-order harmonic generation using spatial light modulators" [Rev. Sci. Instrum. 95, 073002 (2024)].

The Review of scientific instruments·2026
Same author

Deep learning-based automated assessment of pulmonary artery indices and surgical approach triage for tetralogy of Fallot from multicenter cardiac computed tomography (CT).

Clinical radiology·2026
Same author

The effects of nitrogen and phosphorus fertilization on nutrient resorption in female and male Populus cathayana.

Plant biology (Stuttgart, Germany)·2026
Same author

Rubisco large and small subunits provide insights into allotetraploidy events from the genus Oryza.

Plant biology (Stuttgart, Germany)·2026
Same author

Energy Bunching from Subcycle Ionization Injection in Laser Wakefield Acceleration.

Physical review letters·2026
Same author

Dimensionality of the reinforced superconductivity in UTe<sub>2</sub>.

Nature communications·2025
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

This study introduces a novel neural network for sequential detection, approximating the optimal sequential probability ratio test (SPRT). This data-driven approach offers similar performance without needing probability density functions.

Area of Science:

  • Machine Learning
  • Signal Processing
  • Statistical Inference

Background:

  • Sequential detection is crucial in various fields, but optimal methods like the sequential probability ratio test (SPRT) often require detailed statistical models.
  • Conventional supervised learning struggles with variable-length data sequences common in sequential detection tasks.

Purpose of the Study:

  • To propose a novel neural-network-based method for sequential detection.
  • To adapt the optimal parametric sequential probability ratio test (SPRT) for neural network architectures.
  • To demonstrate that a neural network can learn SPRT decision functions from data, offering a nonparametric alternative.

Main Methods:

  • A neural network architecture comprising context units and a feedforward network was designed.

Related Experiment Videos

  • The temporal difference (TD) learning algorithm, a reinforcement learning technique, was employed to train the neural network on observation data.
  • The neural network was trained using independent and identically distributed (iid) observations.

    • Main Results:

    • The developed neural-network sequential detector closely approximates the performance of the optimal SPRT.
    • The neural network successfully learned SPRT decision functions from data.
    • Simulations on iid Gaussian data confirmed comparable performance between the neural network detector and the SPRT.

    Conclusions:

    • The proposed neural network offers a powerful, nonparametric approach to sequential detection.
    • This method bypasses the need for explicit probability density functions, simplifying implementation.
    • The neural network demonstrates robust performance, achieving results similar to the established SPRT.