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 programmable interface to neuromolecular computing networks

K Akingbehin1

  • 1Department of Computer and Information Science, University of Michigan-Dearborn 48128, USA.

Bio Systems
|January 1, 1995
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 journal

Ruliological Resilience: Pattern Restoration and Robustness in Wolfram Patterns. A Basis for Regeneration, Not Just in Cone Shells?

Bio Systems·2026
Same journal

The quantum-to-classical transducer: A thermodynamic and quantum mechanical framework for the emergence of bioenergetics.

Bio Systems·2026
Same journal

Forward-backward gene expression binarization for boolean state inference over a known regulatory network.

Bio Systems·2026
Same journal

Partial-label metric ceilings for evaluating gene regulatory networks inferred from single-cell foundation models.

Bio Systems·2026
Same journal

The impedance mismatch theory: A non-equilibrium thermodynamic framework for a shared energetic stress pathway in neurodegeneration.

Bio Systems·2026
Same journal

Immune signal-status misclassification: A theoretical framework for biological status assignment and failed status resolution.

Bio Systems·2026
See all related articles

This study introduces a programmable interface for reaction-diffusion neural networks, combining programmability with adaptability for complex problem-solving. The novel mesh network architecture shows performance comparable to traditional feedforward networks.

Area of Science:

  • Computational Neuroscience
  • Artificial Intelligence
  • Network Science

Background:

  • Traditional artificial neural networks often use adaline neurons and feedforward topologies.
  • Complex problems require adaptable and programmable solutions that integrate learning and decision-making capabilities.
  • Simulated neural networks offer a platform for exploring novel architectures and functionalities.

Purpose of the Study:

  • To introduce a programmable interface for a simulated network of reaction-diffusion neurons.
  • To combine programmability with adaptability for innovative solutions to complex problems.
  • To evaluate the performance of a mesh reaction-diffusion network against conventional feedforward adaline networks.

Main Methods:

  • Development of a programmable interface with 'learn' and 'decide' syntactic constructs.

Related Experiment Videos

  • Implementation of a simulated network using reaction-diffusion neurons in a mesh topology.
  • Comparison of the mesh reaction-diffusion network's performance with feedforward adaline networks.

    • Main Results:

    • The programmable interface successfully integrates conventional programming with adaptive constructs.
    • The mesh reaction-diffusion network demonstrates performance comparable to conventional feedforward adaline networks.
    • Enhancements for incorporating short-term and long-term memory into the network were described.

    Conclusions:

    • The hybrid approach of combining programmability and adaptability offers innovative solutions.
    • Reaction-diffusion neurons in a mesh topology provide a viable alternative to traditional adaline feedforward networks.
    • The described memory enhancements pave the way for more sophisticated neural network simulations.