Jove
Visualize
Contact Us

Related Experiment Videos

Neural network control systems that learn to perform appropriately.

J A Bullinaria1, P M Riddell

  • 1Department of Psychology, The University of Reading, UK. j.bullinaria@physics.org

International Journal of Neural Systems
|April 20, 2001
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

Children's Accommodation to a Variety of Targets - A Pilot Study.

Strabismus·2017
Same author

Attention processes in children with movement difficulties, reading difficulties or both.

Journal of abnormal child psychology·2006
Same author

Development of the response AC/A ratio over the first year of life.

Vision research·2002
Same author

Variations in accommodation and convergence responses in a minimally controlled photorefractive setting.

Optometry and vision science : official publication of the American Academy of Optometry·2002
Same author

The response to prism deviations in human infants.

Current biology : CB·1999
Same author

Developing visual systems and exposure to virtual reality and stereo displays: some concerns and speculations about the demands on accommodation and vergence.

Applied ergonomics·1999
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles
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

This study explores neural network control systems, focusing on cost functions, initial weights, and learning rates. Simulations of the human oculomotor system reveal insights for improving engineering control applications.

Area of Science:

  • Neuroscience
  • Computer Science
  • Control Theory

Background:

  • Neural networks offer a feasible alternative to direct programming for complex engineering control systems.
  • Understanding the learning process in neural networks is crucial for optimizing their performance.

Purpose of the Study:

  • To examine the impact of cost functions, initial connection weights, and learning rates on neural network control systems.
  • To simulate a simplified human oculomotor system to compare with evolved biological systems.
  • To identify potential improvements for human-like control systems and apply findings to novel engineering applications.

Main Methods:

  • Utilized explicit simulations of a toy model representing a simplified human oculomotor control system.
  • Investigated the influence of gradient descent learning algorithm parameters, including cost function details.

Related Experiment Videos

  • Analyzed system dependency on initial pre-learning connection weights and learning rate patterns.

    • Main Results:

    • Demonstrated how specific choices in cost functions, initial weights, and learning rates affect neural network control system behavior.
    • Provided a comparative analysis between simulated and human-evolved oculomotor control systems.
    • Identified key factors influencing the efficacy of learning algorithms in control system formulation.

    Conclusions:

    • The study highlights the critical role of parameter selection in neural network-based control systems.
    • Findings offer a foundation for enhancing existing control systems and developing new ones for engineering applications.
    • The research paves the way for creating advanced control systems beyond human analogues by leveraging learned principles.