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 learning classifier system with self-adaptive constructivism for mobile robot control.

Jacob Hurst1, Larry Bull

  • 1Faculty of Computing, Engineering & Mathematical Sciences, University of the West of England, Bristol, BS16 1QY, UK.

Artificial Life
|July 25, 2006
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

Neurons as Autoencoders.

Artificial life·2024
Same author

On Recombination.

Artificial life·2024
Same author

A Systematic Review of Machine-Learning Solutions in Anaerobic Digestion.

Bioengineering (Basel, Switzerland)·2023
Same author

Integrated Science Teaching in Atmospheric Ice Nucleation Research: Immersion Freezing Experiments.

Journal of chemical education·2023
Same author

Distorted TCR repertoires define multisystem inflammatory syndrome in children.

PloS one·2022
Same author

A Generalised Dropout Mechanism for Distributed Systems.

Artificial life·2022
Same journal

If Turing Played Piano With an Artificial Partner.

Artificial life·2026
Same journal

Discovering Partial Differential Equations With Neural Cellular Automata.

Artificial life·2026
Same journal

Book Review: Exploring the Boundaries of Life-as-It-Is.

Artificial life·2026
Same journal

System 0/1/2/3: Quad-Process Theory for Multitimescale Embodied Collective Cognitive Systems.

Artificial life·2025
Same journal

To Engineer an Angel, First Validate the Devil: Analyzing the "Could Be" in Artificial Life's "Life as-It-Could-Be".

Artificial life·2025
Same journal

Untapped Potential in Self-Optimization of Hopfield Networks: The Creativity of Unsupervised Learning.

Artificial life·2025
See all related articles

This study introduces a novel neural learning classifier system architecture inspired by constructivism. The system demonstrates adaptable learning and emergent complexity for artificial autonomy, validated in simulations and on a mobile robot.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Robotics

Background:

  • Achieving true autonomy and complex lifelike behavior in artificial entities requires adaptable learning algorithms.
  • Adaptability in learning involves environmental flexibility and an open-ended capacity for acquiring new behaviors.

Purpose of the Study:

  • To explore constructivism-inspired mechanisms within a neural learning classifier system architecture.
  • To investigate parameter self-adaptation as a method for realizing adaptable and autonomous behavior in artificial entities.

Main Methods:

  • Utilized a neural learning classifier system architecture.
  • Implemented a rule structure where each rule is represented by an artificial neural network.
  • Employed parameter self-adaptation for emergent rule complexity and behavior adaptation.

Related Experiment Videos

Main Results:

  • Demonstrated that internal rule complexity emerges during learning at a learner-controlled rate.
  • Showcased that the emergent structure reflects underlying task features.
  • Validated the approach in simulated mazes and on a physical mobile robot platform.

Conclusions:

  • The proposed constructivism-inspired neural learning classifier system effectively facilitates adaptable learning and emergent complexity.
  • Parameter self-adaptation is a viable mechanism for developing autonomous artificial entities capable of complex behaviors.
  • The system's performance in both simulated and real-world robotic tasks highlights its potential for advanced AI development.