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 Concept Videos

Reconstruction of Signal using Interpolation01:10

Reconstruction of Signal using Interpolation

682
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
682
Echo01:06

Echo

880
The human ear cannot distinguish between two sources of sound if they happen to reach within a specific time interval, typically 0.1 seconds apart. More than this, and they are perceived as separate sources.
Imagine the sound is reflected back to the ears. Assuming that the source is very close to the human, the difference between hearing the two sounds—the emitted sound and the reflected sound—may be more than the minimum time for perceiving distinct sounds. If this is the case,...
880
State Space Representation01:27

State Space Representation

519
The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...
519
Deconvolution01:20

Deconvolution

537
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
537

You might also read

Related Articles

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

Sort by
Same author

Online supervised learning of temporal patterns in biological neural networks under feedback control.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Construction of an enterprise-level global supply chain database.

Nature communications·2025
Same author

Modular architecture confers robustness to damage and facilitates recovery in spiking neural networks modeling <i>in vitro</i> neurons.

Frontiers in neuroscience·2025
Same author

Prediction of unobserved bifurcation by unsupervised extraction of slowly time-varying system parameter dynamics from time series using reservoir computing.

Frontiers in artificial intelligence·2024
Same author

Dynamical predictive coding with reservoir computing performs noise-robust multi-sensory speech recognition.

Frontiers in computational neuroscience·2024
Same author

Computation harvesting from nature dynamics for predicting wind speed and direction.

PloS one·2023

Related Experiment Video

Updated: Jan 13, 2026

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

2.0K

Unsupervised Learning in Echo State Networks for Input Reconstruction.

Taiki Yamada1, Yuichi Katori2, Kantaro Fujiwara1

  • 1Graduate School of Information Science and Technology, University of Tokyo, Bunkyo, Tokyo 113-0033, Japan.

Neural Computation
|October 29, 2025
PubMed
Summary

Echo state networks (ESNs) can reconstruct input time series using unsupervised learning (UL) without target outputs. This leverages known ESN parameters, reducing reliance on supervision for tasks like noise filtering.

More Related Videos

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.4K
Combined Shuttle-Box Training with Electrophysiological Cortex Recording and Stimulation as a Tool to Study Perception and Learning
08:43

Combined Shuttle-Box Training with Electrophysiological Cortex Recording and Stimulation as a Tool to Study Perception and Learning

Published on: October 22, 2015

10.7K

Related Experiment Videos

Last Updated: Jan 13, 2026

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

2.0K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.4K
Combined Shuttle-Box Training with Electrophysiological Cortex Recording and Stimulation as a Tool to Study Perception and Learning
08:43

Combined Shuttle-Box Training with Electrophysiological Cortex Recording and Stimulation as a Tool to Study Perception and Learning

Published on: October 22, 2015

10.7K

Area of Science:

  • Computational Neuroscience
  • Machine Learning
  • Recurrent Neural Networks

Background:

  • Echo state networks (ESNs) are recurrent neural networks with fixed input/recurrent layers and a trainable readout layer.
  • ESNs excel at computationally efficient time-series data processing.
  • Traditional ESN training relies on supervised learning with target outputs.

Purpose of the Study:

  • To investigate unsupervised learning (UL) for input reconstruction (IR) in ESNs.
  • To demonstrate that IR is achievable without supervised targets by exploiting known ESN parameters.
  • To explore applications of UL-based IR in dynamical system replication and noise filtering.

Main Methods:

  • Formulating input reconstruction as an unsupervised learning problem.
  • Utilizing known a priori ESN parameters that satisfy invertibility conditions.
  • Developing UL-based algorithms for ESN input reconstruction.

Main Results:

  • Input reconstruction in ESNs can be achieved via unsupervised learning.
  • Known ESN parameters, when invertible, enable UL-based IR without supervised targets.
  • UL-based IR algorithms are suitable for autonomous processing and dynamical system replication.

Conclusions:

  • Prior knowledge of ESN parameters can significantly reduce the need for supervised learning.
  • Exploiting specific values of fixed network parameters offers a new principle for ESN design.
  • UL-based ESNs provide insights into potential brain computational mechanisms and advance computational neuroscience models.