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

Embedded neural networks: exploiting constraints.

Christian Scheier1, Rolf Pfeifer, Yasuo Kunyioshi

  • 1Artificial Intelligence Laboratory, University of Zurich, Winterthurerstrasse 190, 8057, Zurich, Switzerland

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 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

Exploiting the Dynamics of Soft Materials for Machine Learning.

Soft robotics·2018
Same author

A cable-driven soft robot surgical system for cardiothoracic endoscopic surgery: preclinical tests in animals.

Surgical endoscopy·2016
Same author

Information processing via physical soft body.

Scientific reports·2015
Same author

Mechanical catalysis on the centimetre scale.

Journal of the Royal Society, Interface·2015
Same author

Cognition from the bottom up: on biological inspiration, body morphology, and soft materials.

Trends in cognitive sciences·2014
Same author

A soft body as a reservoir: case studies in a dynamic model of octopus-inspired soft robotic arm.

Frontiers in computational neuroscience·2013
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

New results on prescribed-time synchronization of complex networks via intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Variance-constrained multi-view ensemble broad network for imbalanced data.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Embedding neural networks in robot bodies leverages physical constraints for efficient learning. This embodied approach simplifies networks, enabling real-time responses and offering new insights into cognitive science principles.

Area of Science:

  • Cognitive Science
  • Robotics
  • Artificial Intelligence

Background:

  • Embodied cognitive science explores how physical bodies influence cognitive processes.
  • Neural networks are powerful computational models but often lack grounding in physical interaction.
  • Integrating neural networks into robotic bodies presents an opportunity to leverage physical embodiment for enhanced learning.

Purpose of the Study:

  • To investigate the implications of embedding neural networks within a robot's physical structure.
  • To demonstrate how physical constraints can be exploited for efficient neural network learning.
  • To offer new perspectives on focus-of-attention and object constancy within embodied AI.

Main Methods:

  • Utilizing concepts from embodied cognitive science to analyze robot-environment interactions.

Related Experiment Videos

  • Designing neural networks that incorporate environmental, morphological, and motor system constraints.
  • Conducting case studies with simulated and physical mobile robots using both hand-designed and evolved neural networks.

    • Main Results:

    • Embedding neural networks in physical bodies imposes constraints that simplify learning.
    • Constraint-based network design leads to efficient, task-suited networks with real-time capabilities.
    • The approach provides novel insights into focus-of-attention and object constancy in embodied agents.

    Conclusions:

    • Designing embedded neural networks requires understanding and exploiting physical constraints.
    • Embodied AI offers a path towards more efficient and responsive intelligent systems.
    • This research bridges embodied cognition and artificial intelligence through practical robotic implementations.