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

A neural network model for limb trajectory formation.

L Massone1, E Bizzi

  • 1Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge 02139.

Biological Cybernetics
|January 1, 1989
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

Recurrent pericarditis in children: Clinical and therapeutic differences from adults.

International journal of cardiology·2026
Same author

Depemokimab and the twice-yearly regimen: pharmacological implications and therapeutic positioning in severe eosinophilic respiratory diseases.

Frontiers in immunology·2026
Same author

Fetal-hope study: Home monitoring of fetal heart rate in SSA + pregnant women: Rationale and design.

European journal of obstetrics, gynecology, and reproductive biology·2024
Same author

The first case of systemic lupus erythematosus (SLE) triggered by COVID-19 infection.

European review for medical and pharmacological sciences·2020
Same author

HyalOne® in the treatment of symptomatic hip OA - data from the ANTIAGE register: seven years of observation.

European review for medical and pharmacological sciences·2017
Same author

An open randomized active-controlled clinical trial with low-dose SKA cytokines versus DMARDs evaluating low disease activity maintenance in patients with rheumatoid arthritis.

Drug design, development and therapy·2017
Same journal

Harmonic memory in phasor neural networks.

Biological cybernetics·2026
Same journal

Correction: Decreased spinal inhibition leads to undiversified locomotor patterns.

Biological cybernetics·2026
Same journal

Foundational issues of network models in biology.

Biological cybernetics·2026
Same journal

Dynamical mechanisms for coordinating long-term working memory based on the precision of spike-timing in cortical neurons.

Biological cybernetics·2026
Same journal

Distinct dopaminergic spike-timing-dependent plasticity rules are suited to different functional roles.

Biological cybernetics·2026
Same journal

Fluctuation-response relations for a two-stage population of spiking neurons stimulated by common noise.

Biological cybernetics·2026
See all related articles

This study demonstrates how a neural network can learn to generate limb aiming movements, successfully mimicking biological movement patterns and solving motor redundancy challenges.

Area of Science:

  • Computational Neuroscience
  • Robotics
  • Biomechanical Engineering

Background:

  • Generating realistic limb movements is crucial for robotics and understanding biological motor control.
  • Previous models often struggle with the complexity and redundancy inherent in biological movements.

Purpose of the Study:

  • To develop and evaluate a neural network architecture capable of representing and generating unconstrained limb aiming movements.
  • To investigate the network's learning capabilities, internal organization, and generalization performance.

Main Methods:

  • A three-layer sequential neural network was trained to produce time trajectories for limb movements.
  • The network was coupled with a mechanical limb model where muscles were represented as springs.
  • Training utilized a bell-shaped velocity profile, characteristic of biological movements.

Related Experiment Videos

Main Results:

  • The neural network successfully learned and generalized limb aiming movements, adjusting velocity profiles accurately.
  • Internal network connections organized into functional zones, encoding key movement features.
  • The model demonstrated robustness to input noise and exhibited attractor dynamics.
  • The coupled system effectively addressed the motor redundancy problem.

Conclusions:

  • Sequential neural networks can effectively model sensory-motor transformations for generating complex limb movements.
  • The spring-based muscle representation within a mechanical model aids in solving motor redundancy.
  • This approach offers a promising framework for understanding and replicating biological motor control.