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

Stochastic reservoir computers.

Peter J Ehlers1, Hendra I Nurdin2, Daniel Soh3

  • 1Wyant College of Optical Sciences, University of Arizona, Tuscon, AZ, US. ehlersp@arizona.edu.

Nature Communications
|March 29, 2025
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

Improving the performance of echo state networks through state feedback.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Single photon quantum filtering using non-Markovian embeddings.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2012
Same author

On structure-preserving transformations of the Ito generator matrix for model reduction of quantum feedback networks.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2012
Same author

Designing quantum memories with embedded control: photonic circuits for autonomous quantum error correction.

Physical review letters·2010
Same journal

Chlorinated VSLSs Surpass HCFCs in CFC-11-Equivalent Emissions for Ozone Layer Depletion in China.

Nature communications·2026
Same journal

Author Correction: Charge transfer in triphenylamine-tetrazine covalent organic frameworks for solar-driven hydrogen peroxide production.

Nature communications·2026
Same journal

Vegetation browning patterns under compound soil and atmospheric dryness in northern permafrost ecosystems.

Nature communications·2026
Same journal

Voltage imaging of CA1 pyramidal cells and SST+ interneurons reveals stability and plasticity mechanisms of spatial firing.

Nature communications·2026
Same journal

Radical-omics reveals the hydrogen-abstraction pathway of isoprene oxidation.

Nature communications·2026
Same journal

Toughening elastomer via sequentially activated multi-pathway energy dissipation.

Nature communications·2026
See all related articles

Stochastic reservoir computers, using probabilities as readouts, offer compact size and universal approximation capabilities. These systems show improved performance in classification and time series prediction compared to deterministic models.

Area of Science:

  • Machine Learning
  • Quantum Computing
  • Dynamical Systems

Background:

  • Reservoir computing leverages nonlinear dynamical systems for efficient machine learning.
  • Quantum reservoir computing introduces inherent stochasticity.
  • Traditional methods often require large hardware footprints.

Purpose of the Study:

  • Investigate the universality of stochastic reservoir computers.
  • Explore readouts based on reservoir state probabilities for compact hardware.
  • Analyze performance in classification and chaotic time series prediction.

Main Methods:

  • Utilizing probabilities of stochastic reservoir states as readouts.
  • Proving universality for classes of stochastic echo state networks.
  • Evaluating performance on classification and chaotic time series prediction tasks.

Related Experiment Videos

Main Results:

  • Demonstrated that stochastic echo state networks form universal approximating classes.
  • Achieved significantly improved performance over deterministic counterparts in specific tasks.
  • Identified shot noise as a performance-limiting factor.

Conclusions:

  • Stochastic reservoir computing with probability-based readouts enables compact and powerful universal approximators.
  • These systems offer a promising alternative to deterministic reservoir computers, especially under low noise conditions.