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

Isotropic sequence order learning.

Bernd Porr1, 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
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

We developed an isotropic unsupervised algorithm for temporal sequence learning. This algorithm enables robots to learn collision avoidance through sensor-motor feedback loops without explicit reward signals.

Area of Science:

  • Computational Neuroscience
  • Machine Learning
  • Robotics

Background:

  • Temporal sequence learning is crucial for understanding complex behaviors.
  • Unsupervised learning algorithms offer a powerful framework for biological and artificial systems.
  • Existing methods often rely on specific reward signals, limiting their applicability.

Purpose of the Study:

  • To introduce a novel isotropic unsupervised algorithm for temporal sequence learning.
  • To investigate the algorithm's performance in both open-loop and closed-loop conditions.
  • To demonstrate the algorithm's capability in enabling adaptive behaviors like collision avoidance in robots.

Main Methods:

  • Bandpass filtering of all input signals before convergence to a linear output neuron.

Related Experiment Videos

  • Synaptic weight changes based on the correlation between filtered inputs and the output derivative.
  • Implementation in a simulated robot with a retraction reflex for closed-loop collision avoidance.

    • Main Results:

    • Analytical calculation of weight change in open-loop, showing similarity to spike-time-dependent plasticity.
    • Automatic stabilization of synaptic weights without normalization when temporal differences cease.
    • Successful collision avoidance learning in a robot using isotropic sequence order (ISO) learning.

    Conclusions:

    • The proposed isotropic unsupervised algorithm effectively learns temporal sequences.
    • ISO learning provides a biologically plausible mechanism for sensor-motor adaptation and collision avoidance.
    • The algorithm demonstrates stable learning and potential for integration with other reinforcement learning models.