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

Coevolution of active vision and feature selection.

Dario Floreano1, Toshifumi Kato, Davide Marocco

  • 1Autonomous Systems Lab, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland. Dario.Floreano@epfl.ch

Biological Cybernetics
|March 31, 2004
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

JOINclusion: A serious mobile game for promoting ethnocultural empathy in schools.

The British journal of developmental psychology·2026
Same author

Edible Pneumatic Battery for Sustained and Repeated Robot Actuation.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025
Same author

Predicting Cognitive Decline in Parkinson's Disease Using Artificial Neural Networks: An Explainable AI Approach.

Brain sciences·2025
Same author

Human Expertise and Large Language Model Embeddings in the Content Validity Assessment of Personality Tests.

Educational and psychological measurement·2025
Same author

Digital Screening for Early Identification of Cognitive Impairment: A Narrative Review.

Wiley interdisciplinary reviews. Cognitive science·2025
Same author

Edible aquatic robots with Marangoni propulsion.

Nature communications·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

Simple AI architectures tackle complex visual tasks like shape recognition and navigation. Coevolutionary processes enable machines to learn by interacting with environments, developing insect-like visual strategies.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Robotics

Background:

  • Complex visual tasks pose challenges for AI.
  • Simulating biological vision systems is an active research area.

Purpose of the Study:

  • To demonstrate that simple AI architectures can solve complex visual tasks.
  • To explore coevolutionary processes for developing AI vision systems.

Main Methods:

  • Coevolutionary algorithms were used to generate AI architectures.
  • Behavioral machines with primitive vision systems interacted with environments.
  • Experiments included shape discrimination, car driving, and robot navigation.

Main Results:

  • AI systems achieved position- and size-invariant shape recognition.

Related Experiment Videos

  • Developed sensitivity to oriented edges, corners, and height.
  • Exhibited behaviors similar to insect visual strategies for feature localization.

    • Conclusions:

    • Simple, coevolved architectures can achieve sophisticated visual capabilities.
    • Active vision and feature selection are key to developing robust AI vision.
    • This approach offers insights into biological visual system evolution.