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

Neural Network Exploration Using Optimal Experiment Design.

David A. Cohn1

  • 1Massachusetts Institute of Technology, USA

Neural Networks : the Official Journal of the International Neural Network Society
|August 1, 1996
PubMed
Summary

Optimal experiment design (OED) guides neural network learners to maximize learning by efficiently exploring domains. This approach minimizes generalization error, offering a valuable strategy for AI development.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same journal

Injecting reasoning into vision-language models via weight-decomposed merging.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

A Non-equilibrium thermodynamic framework for neural networks: A principled correspondence and parameter dynamics.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Dual-pathway mask ranking guided selective fine-tuning for backdoor purification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Discriminative transfer feature learning for unsupervised domain adaptation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

ARetinex-Net: Low-light image enhancement with adaptive retinex model and global illumination representation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

A Multi-Task Learning Framework with Physics Embedded for Signal Reconstruction and State Prediction in Underground Multi-Robot Systems.

Neural networks : the official journal of the International Neural Network Society·2026

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Statistics

Background:

  • Neural networks aim to learn as much as possible.
  • Existing methods may not guarantee efficient domain exploration.

Purpose of the Study:

  • To investigate how to optimize learning in neural networks.
  • To apply optimal experiment design (OED) principles to AI.

Main Methods:

  • Utilized theoretical results from Fedorov (1972) and MacKay (1992).
  • Applied optimal experiment design (OED) techniques.
  • Guided query/action selection for a neural network learner.

Main Results:

  • Demonstrated that OED techniques minimize generalization error.

Related Experiment Videos

  • Showcased efficient and complete domain exploration by the learner.
  • Identified OED as a valuable tool for AI, despite computational costs.

    • Conclusions:

    • OED-based query/action selection is effective for maximizing learning.
    • This method offers significant advantages in specific AI domains.
    • Computational cost is a factor to consider for OED implementation.