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

Stability criteria for unsupervised temporal association networks.

Guy Wallis1

  • 1Department of Experimental Psychology, Oxford University, Oxford, OX1 3UD, UK. gwallis@hms.uq.edu.au

IEEE Transactions on Neural Networks
|March 25, 2005
PubMed
Summary

This study introduces a new unsupervised learning rule for extracting object features, enhancing object recognition. Tailored learning rules improve accuracy and speed while ensuring stable performance.

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

Schizotypy and perceptual span in a non-clinical sample: a virtual reality study.

Cognitive neuropsychiatry·2024
Same author

Express Visuomotor Responses Reflect Knowledge of Both Target Locations and Contextual Rules during Reaches of Different Amplitudes.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2023
Same author

Symbolic cues enhance express visuomotor responses in human arm muscles at the motor planning rather than the visuospatial processing stage.

Journal of neurophysiology·2022
Same author

Visual-haptic integration, action and embodiment in virtual reality.

Psychological research·2021
Same author

Trial-by-trial modulation of express visuomotor responses induced by symbolic or barely detectable cues.

Journal of neurophysiology·2021
Same author

Microsaccades and covert attention: Evidence from a continuous, divided attention task.

Journal of eye movement research·2021

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computer Vision

Background:

  • Unsupervised learning rules are crucial for extracting object features in machine learning.
  • Object recognition tasks require efficient and stable feature extraction methods.
  • Existing learning rules may lack adaptability to diverse input spaces.

Purpose of the Study:

  • To describe a biologically realizable, unsupervised learning rule for online object feature extraction.
  • To propose modifications for adapting the learning rule to specific input spaces.
  • To model and ensure learning stability in modified learning rules.

Main Methods:

  • Developed a biologically realizable unsupervised learning rule for online feature extraction.
  • Proposed alterations to the basic learning rule for input space adaptability.

Related Experiment Videos

  • Utilized digital filtering techniques to model learning instability criteria.
  • Tested predicted regions of stability and instability.

    • Main Results:

    • A family of adaptable learning rules was generated.
    • Modified rules demonstrated improved convergence times and accuracy compared to the standard rule.
    • The proposed methods successfully ensured learning stability.
    • The learning rules are suitable for a range of object recognition tasks.

    Conclusions:

    • Tailored unsupervised learning rules offer enhanced performance in object recognition.
    • Adaptability and stability are key considerations for effective machine learning algorithms.
    • The developed learning rules provide a robust solution for online feature extraction.