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

Probabilistic computation by neuromine networks.

R D Hangartner1, P Cull

  • 1Cray Inc., Seattle, WA 98104, USA. hangarr@pdx.or.com

Bio Systems
|February 13, 2001
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

Teaching general practitioners to teach.

Medical teacher·2014
Same author

Letters.

Medical teacher·2014
Same author

An unusual case of neonatal ileus.

Emergency medicine journal : EMJ·2009
Same author

Gene verification and discovery by Walking Tree Method.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2001
Same author

A ternary logic model for recurrent neuromime networks with delay.

Biological cybernetics·1995
Same author

Aligning genomes with inversions and swaps.

Proceedings. International Conference on Intelligent Systems for Molecular Biology·1994
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

Biologically feasible neural nets can compute beyond deterministic polynomial time limits by incorporating randomness. This study demonstrates how neural networks can generate random bits, enabling probabilistic computations and expanding their computational power.

Area of Science:

  • Computational neuroscience
  • Theoretical computer science
  • Artificial intelligence

Background:

  • Classical neural networks are limited by deterministic polynomial time algorithms.
  • Recent advances in randomized algorithms suggest potential for enhanced computation.
  • The plausibility of neural network computation beyond classical limits is explored.

Purpose of the Study:

  • To investigate if biologically feasible neural networks can compute beyond deterministic polynomial time.
  • To explore the integration of randomized algorithms within neural network architectures.
  • To demonstrate probabilistic computation using neural nets with limited precision.

Main Methods:

  • Constructing simple neural networks with reciprocal inhibition and tonic input to generate random bits.

Related Experiment Videos

  • Utilizing microscopic noise in analog computation to produce macroscopic random bits.
  • Connecting a random bit generator to a neural network representing deterministic algorithms.

    • Main Results:

    • A basic neural network configuration reliably produces random bits.
    • These random bits can be used to implement probabilistic computations.
    • Neural networks demonstrate the capability to perform computations beyond classical limitations.

    Conclusions:

    • Biologically feasible neural networks can perform probabilistic computations.
    • The integration of random bit generation expands the computational power of neural networks.
    • These findings suggest neural networks can overcome limitations of deterministic algorithms.