Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Propagation of Uncertainty from Systematic Error

Propagation of Uncertainty from Systematic Error

The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...

Propagation of Uncertainty from Random Error

Propagation of Uncertainty from Random Error

An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Efficient optimisation of physical reservoir computers using only a delayed input.

Communications engineering·2025

Same author

Transfer learning for photonic delay-based reservoir computing to compensate parameter drift.

Nanophotonics (Berlin, Germany)·2024

Same author

Noise-injected analog Ising machines enable ultrafast statistical sampling and machine learning.

Nature communications·2022

Same author

Space division multiplexing in standard multi-mode optical fibers based on speckle pattern classification.

Scientific reports·2019

Same author

A poor man's coherent Ising machine based on opto-electronic feedback systems for solving optimization problems.

Nature communications·2019

Search research articles

Related Experiment Video

Updated: Oct 22, 2025

A Photonic System for Generating Unconditional Polarization-Entangled Photons Based on Multiple Quantum Interference

A Photonic System for Generating Unconditional Polarization-Entangled Photons Based on Multiple Quantum Interference

Published on: September 5, 2019

Photonic Reservoir Computer with Output Expansion for Unsupervized Parameter Drift Compensation.

Jaël Pauwels^1,2, Guy Van der Sande², Guy Verschaffelt²

¹Laboratoire d'Information Quantique, Université Libre de Bruxelles, B-1050 Bruxelles, Belgium.

Entropy (Basel, Switzerland)

|August 27, 2021

Summary

We improved reservoir computer performance by adding random nonlinear output neurons. This method partially recovers performance in systems with parameter drift, balancing gains with complexity.

Keywords:

coherent optical reservoir output expansion photonic computing readout weight-tuning reservoir computing unsupervised noise compensation

More Related Videos

Quantum State Engineering of Light with Continuous-wave Optical Parametric Oscillators

Quantum State Engineering of Light with Continuous-wave Optical Parametric Oscillators

Published on: May 30, 2014

Generation and Coherent Control of Pulsed Quantum Frequency Combs

Generation and Coherent Control of Pulsed Quantum Frequency Combs

Published on: June 8, 2018

Related Experiment Videos

Last Updated: Oct 22, 2025

A Photonic System for Generating Unconditional Polarization-Entangled Photons Based on Multiple Quantum Interference

A Photonic System for Generating Unconditional Polarization-Entangled Photons Based on Multiple Quantum Interference

Published on: September 5, 2019

Quantum State Engineering of Light with Continuous-wave Optical Parametric Oscillators

Quantum State Engineering of Light with Continuous-wave Optical Parametric Oscillators

Published on: May 30, 2014

Generation and Coherent Control of Pulsed Quantum Frequency Combs

Generation and Coherent Control of Pulsed Quantum Frequency Combs

Published on: June 8, 2018

Area of Science:

Complex Systems
Machine Learning
Optoelectronics

Background:

Reservoir computing (RC) is a powerful framework for time-series processing.
RC systems can degrade over time due to parameter drift.
Improving RC performance often involves complex retraining or hardware changes.

Purpose of the Study:

To introduce a method for enhancing reservoir computer performance without altering the fixed reservoir.
To demonstrate the effectiveness of an expanded output layer in recovering performance.
To explore the trade-off between performance enhancement and system complexity.

Main Methods:

The core reservoir of the computing system was kept fixed.
Additional output neurons were introduced as random nonlinear functions of existing reservoir neurons.
The method was tested on an experimental opto-electronic system exhibiting parameter drift.

Main Results:

The expanded output layer successfully improved the performance of the reservoir computer.
Partial recovery of lost performance was achieved in the presence of parameter drift.
The proposed scheme offers a tunable trade-off between performance improvement and added complexity.

Conclusions:

Expanding the output layer is an effective strategy to boost reservoir computing performance.
This approach provides a practical solution for mitigating performance degradation in real-world systems.
The method offers flexibility in system design, allowing for customized performance-complexity balances.