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

Connection and coordination: the interplay between architecture and dynamics in evolved model pattern generators.

Sean Psujek1, Jeffrey Ames, Randall D Beer

  • 1Department of Biology, Case Western Reserve University, Cleveland, OH 44106, USA. sean.psujek@case.edu

Neural Computation
|February 18, 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

When can neuronal activity-dependent homeostatic plasticity maintain circuit-level properties?

Journal of computational neuroscience·2026
Same author

Matters of life and death in computational cell biology.

NPJ systems biology and applications·2026
Same author

Social contingency in embodied neural networks relies on co-constructed dynamical mechanisms.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2026
Same author

The role of signal in saltatory pursuit of cryptic stationary targets.

Movement ecology·2025
Same author

MATTERS OF LIFE AND DEATH IN COMPUTATIONAL CELL BIOLOGY.

ArXiv·2025
Same author

Repeat ultrasound in pediatric EDs improves appendicitis diagnosis after referral imaging.

Frontiers in pediatrics·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

Neural architecture significantly impacts the dynamics of evolved walking pattern generators. Specific architectural motifs and parameter subgroups, defined by neuron excitability and connection signs, are crucial for high fitness and evolutionary potential.

Area of Science:

  • Computational neuroscience
  • Evolutionary robotics
  • Biologically inspired computing

Background:

  • Neural networks are fundamental to biological and artificial locomotion.
  • Understanding the relationship between neural architecture and emergent dynamics is key for designing effective control systems.
  • Evolved neural networks offer insights into efficient and robust solutions for complex tasks like walking.

Purpose of the Study:

  • To systematically investigate how neural architecture influences the dynamics of evolved pattern generators for walking.
  • To identify critical architectural features and parameter configurations that lead to high performance and evolutionary success.
  • To explore the relationship between neural architecture, parameter subgroups, and their functional characteristics.

Main Methods:

Related Experiment Videos

  • Systematic analysis of evolved neural network architectures for a walking task.
  • Evaluation of the minimum number of connections required for high performance.
  • Identification and characterization of architectural motifs associated with high fitness.
  • Examination of the evolutionary divergence of high-fitness architectures.
  • Demonstration and analysis of distinct parameter subgroups within architectures.

Main Results:

  • The study identified minimum connection requirements for effective walking pattern generation.
  • Specific architectural motifs were found to be strongly associated with high fitness in evolved controllers.
  • High-fitness architectures exhibited varying degrees of evolutionary adaptability.
  • Distinct parameter subgroups were observed in certain architectures, correlating with neuron excitability and connection sign differences.

Conclusions:

  • Neural architecture plays a critical role in shaping the dynamics and performance of evolved walking controllers.
  • Identifying key architectural motifs and understanding parameter subgroup characteristics can guide the design of more efficient and adaptable artificial locomotion systems.
  • This research provides a deeper understanding of the interplay between structure, evolution, and function in neural pattern generators.