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

ISO learning approximates a solution to the inverse-controller problem in an unsupervised behavioral paradigm.

Bernd Porr1, Christian von Ferber, Florentin Wörgötter

  • 1Department of Psychology, University of Stirling, Scotland. bp1@cn.stir.ac.uk

Neural Computation
|April 12, 2003
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

This study introduces Isotropic Sequence Order (ISO) learning, a novel algorithm for temporal sequence learning. ISO learning enables anticipatory actions by learning an inverse controller, advancing motor control beyond reactive reflexes.

Area of Science:

  • Robotics
  • Control Theory
  • Machine Learning

Background:

  • Traditional reflex reactions are reactive, leading to delayed responses after a disturbance.
  • A need exists for systems that can anticipate and act proactively rather than reactively.

Purpose of the Study:

  • To embed the novel Isotropic Sequence Order (ISO) learning algorithm into a teacher-free sensor-motor feedback environment.
  • To demonstrate that ISO learning enables anticipatory actions, overcoming the limitations of fixed reflex reactions.
  • To analytically show the system learns the inverse controller of its own reflex through control theory.

Main Methods:

  • Implementing the ISO learning algorithm within a formal, nonevaluating environment.
  • Establishing a sensor-motor feedback loop guided initially by fixed reflex reactions.

Related Experiment Videos

  • Applying control theory to analytically demonstrate the learning process.

    • Main Results:

    • The system transitions from reactive reflex-loop reactions to proactive, anticipatory actions.
    • The learning process is analytically demonstrated to be equivalent to learning the inverse controller of the system's reflex.
    • The system successfully learns a basic form of feedforward motor control.

    Conclusions:

    • ISO learning offers a significant advancement over traditional reactive control systems.
    • The integration of ISO learning into a sensor-motor loop facilitates anticipatory behavior.
    • This research provides a control-theoretic understanding of how systems can learn feedforward motor control through sequence order learning.