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

Chained learning architectures in a simple closed-loop behavioural context.

Tomas Kulvicius1, Bernd Porr, Florentin Wörgötter

  • 1Bernstein Centre for Computational Neuroscience, University of Göttingen, Bunsenstr. 10, 37073 Göttingen, Germany. tomas@bccn-goettingen.de

Biological Cybernetics
|October 4, 2007
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

PriMAT: Robust multi-animal tracking of primates in the wild.

PloS one·2026
Same author

Kinematic modulation across the ontogenetic transition to active social engagement.

Early human development·2026
Same author

Analyzing gaze and hand movement patterns in leader-follower interactions during a time-continuous cooperative manipulation task.

Frontiers in psychology·2026
Same author

Closed-Loop Multistep Planning.

Neural computation·2025
Same author

Computer vision for primate behavior analysis in the wild.

Nature methods·2025
Same author

Comparison of marker-less 2D image-based methods for infant pose estimation.

Scientific reports·2025
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

Chained learning architectures enable stable behavior in robots by temporally correlating sensor cues, outperforming simple learning units, especially with sparse inputs.

Area of Science:

  • Computational Neuroscience
  • Robotics
  • Machine Learning

Background:

  • Living organisms learn through temporal correlation of sensor cues, a process related to classical and operant conditioning.
  • Current algorithmic approaches often rely on simple, single learning units, which can be insufficient for complex behavioral contexts.

Purpose of the Study:

  • To investigate the efficacy of chained learning architectures in a closed-loop behavioral system.
  • To address limitations of simple learning units in scenarios with sparse temporal inputs.

Main Methods:

  • Applied temporal sequence learning to a driving robot tasked with line following within a closed-loop system.
  • Introduced and analyzed two novel chained learning architectures: linear chain and honeycomb chain.
  • Compared the performance of chained architectures against a simple learning unit in both open and closed-loop conditions.

Related Experiment Videos

Main Results:

  • Demonstrated that stable behavior can be achieved using the implemented simple chained learning architectures.
  • Chained architectures showed potential for improved behavioral performance compared to simple architectures.
  • Effectiveness was particularly noted in situations with sparse temporal inputs where simple correlations typically fail.

Conclusions:

  • Simple chained learning architectures are viable for achieving stable, learned behaviors.
  • These architectures offer a promising alternative to single learning units, especially for complex tasks with limited sensory data.
  • Further exploration of chained architectures can lead to enhanced robotic and biological learning models.