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

Curved trajectory prediction using a self-organizing neural network.

J A Marshall1, V Srikanth

  • 1Department of Computer Science, University of North Carolina at Chapel Hill, USA. marshall@computer.org

International Journal of Neural Systems
|May 8, 2000
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

Protocol for evaluation of enhanced models of primary care in the management of stroke and other chronic disease (PRECISE): A data linkage healthcare evaluation study.

International journal of population data science·2021
Same author

Genotype analysis of noroviruses associated with gastroenteritis outbreaks in childcare centres, Victoria, Australia, 2012-2015.

Epidemiology and infection·2017
Same author

The Association of Type 2 Diabetes Mellitus with Cerebral Gray Matter Volume Is Independent of Retinal Vascular Architecture and Retinopathy.

Journal of diabetes research·2016
Same author

Times are changing; researchers need to change too.

European journal of neurology·2016
Same author

Gait phenotype from mild cognitive impairment to moderate dementia: results from the GOOD initiative.

European journal of neurology·2015
Same author

A novel and innovative technique of using a disposable syringe and mesh for harvesting fat for structural fat grafting.

Indian journal of plastic surgery : official publication of the Association of Plastic Surgeons of India·2015

This study introduces a new neural mechanism called disfacilitation to improve visual tracking of curved object paths. This enhances predictions for accelerating and decelerating objects, advancing visual system capabilities.

Area of Science:

  • Computational neuroscience
  • Computer vision
  • Artificial intelligence

Background:

  • Current neural networks excel at tracking linear object motion.
  • Tracking curved trajectories remains a challenge for artificial visual systems.

Purpose of the Study:

  • To introduce and describe a novel neural mechanism, disfacilitation, for enhanced visual trajectory tracking.
  • To computationally demonstrate how this mechanism improves predictions for curved paths.

Main Methods:

  • Development of a neural network model incorporating the disfacilitation mechanism.
  • Computational simulations to analyze the network's learning and predictive capabilities.
  • Testing the model's performance with accelerating and decelerating objects.

Related Experiment Videos

Main Results:

  • The disfacilitation mechanism enables neural networks to track curved trajectories effectively.
  • Simulations show the network learns to accurately track object speed.
  • The model successfully predicts the future locations of objects with changing velocities.

Conclusions:

  • Disfacilitation is a viable neural mechanism for improving visual tracking of complex object movements.
  • This mechanism enhances the predictive accuracy of artificial visual systems for non-linear motion.
  • The findings contribute to more robust object tracking in computer vision and neuroscience.