• Home
  • Search
  • Unsupervised Learning in Echo State Networks for Input Reconstruction.
  • https://doi.org/10.1162/neco.a.38Copy DOI Icon

Unsupervised Learning in Echo State Networks for Input Reconstruction.

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Echo state networks (ESNs) are a class of recurrent neural networks in which only the readout layer is trainable, while the recurrent and input layers are fixed. This architectural constraint enables computationally efficient processing of time-series data. Traditionally, the readout layer in ESNs is trained using supervised learning with target outputs. In this study, we focus on input reconstruction (IR), where the readout layer is trained to reconstruct the input time series fed into the ESN. We show that IR can be achieved through unsupervised learning (UL), without access to supervised targets, provided that the ESN parameters are known a priori and satisfy invertibility conditions. This formulation allows applications relying on IR, such as dynamical system replication and noise filtering, to be reformulated within the UL framework via straightforward integration with existing algorithms. Our results suggest that prior knowledge of ESN parameters can reduce reliance on supervision, thereby establishing a new principle-not only by fixing part of the network parameters but also by exploiting their specific values. Furthermore, our UL-based algorithms for input reconstruction and related tasks are suitable for autonomous processing, offering insights into how analogous computational mechanisms might operate in the brain in principle. These findings contribute to a deeper understanding of the mathematical foundations of ESNs and their relevance to models in computational neuroscience.

Similar Papers
  • Conference Article
  • Citations6

Product reservoir computing: Time-series computation with multiplicative neurons

  • Jul 01, 2015
  • Alireza Goudarzi +2
  • Research Article
  • Citations1

Predicting complex time series with deep echo state networks.

  • Sep 01, 2025
  • Chaos (Woodbury, N.Y.)
  • Afrouz Delshad +1
  • PDF
  • Research Article
  • Citations150

Remaining useful life prediction of PEMFC systems under dynamic operating conditions

  • Jan 29, 2021
  • Energy Conversion and Management
  • Zhiguang Hua +4
  • Research Article
  • Citations13

Optimizing simple deterministically constructed cycle reservoir network with a Redundant Unit Pruning Auto-Encoder algorithm

  • May 16, 2019
  • Neurocomputing
  • Heshan Wang +4
  • Conference Article
  • Citations3

Evolving reservoir weights in the frequency domain

  • Jul 07, 2021
  • Sebastián Basterrech +1
  • Conference Article
  • Citations6

English

  • Jan 01, 2010
  • André Frank Krause +3
  • Conference Article

Echo State Networks in Reservoir Computing: Foundations, Benchmarks, and Applications to Next-G Wireless Communication

  • Nov 12, 2025
  • Andrew Liu +3
  • Research Article
  • Citations35

On the use of Bayesian methods for evaluating compartmental neural models.

  • Jul 01, 1998
  • Journal of Computational Neuroscience
  • Pierre Baldi +2
  • Conference Article
  • Citations9

A CHARACTERIZATION OF THE EDGE OF CRITICALITY IN BINARY ECHO STATE NETWORKS

  • Sep 01, 2018
  • Pietro Verzelli +2
  • Single Book
  • Citations28

Computational Modelling in Behavioural Neuroscience

  • Apr 03, 2009
  • Dietmar Heinke +2
  • PDF
  • Supplementary Content
  • Citations46

Code Generation in Computational Neuroscience: A Review of Tools and Techniques

  • Nov 05, 2018
  • Frontiers in Neuroinformatics
  • Inga Blundell +28
  • Preprint Article

Modeling Neuronal Firing: A Review of The Hodgkin–Huxley Model in Computational Neuroscience

  • Apr 03, 2025
  • Abdullah Choudhary +1
  • PDF
  • Research Article
  • Citations15

A neuro-inspired general framework for the evolution of stochastic dynamical systems: Cellular automata, random Boolean networks and echo state networks towards criticality

  • Jun 11, 2020
  • Cognitive Neurodynamics
  • Sidney Pontes-Filho +8
  • PDF
  • Discussion
  • Citations22

New Light on Chromotherapy: Grakov's ‘Virtual Scanning’ System of Medical Assessment and Treatment

  • Oct 05, 2006
  • Evidence-based Complementary and Alternative Medicine : eCAM
  • Alex Hankey +1
  • PDF
  • Research Article
  • Citations30

Memory-Efficient Synaptic Connectivity for Spike-Timing- Dependent Plasticity.

  • Apr 24, 2019
  • Frontiers in Neuroscience
  • Bruno U Pedroni +8
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.