mlsanityData to 13 Oct 2026

Stochastic Reservoir Computers

arXiv 2405.12382 ↗First posted 20 May 2024cs.LG cs.NE cs.SYcited by 4

Not on the map. Why?

Abstract (arXiv)

Reservoir computing is a form of machine learning that utilizes nonlinear dynamical systems to perform complex tasks in a cost-effective manner when compared to typical neural networks. Many recent advancements in reservoir computing, in particular quantum reservoir computing, make use of reservoirs that are inherently stochastic. However, the theoretical justification for using these systems has not yet been well established. In this paper, we investigate the universality of stochastic reservoir computers, in which we use a stochastic system for reservoir computing using the probabilities of each reservoir state as the readout instead of the states themselves. In stochastic reservoir computing, the number of distinct states of the entire reservoir computer can potentially scale exponentially with the size of the reservoir hardware, offering the advantage of compact device size. We prove that classes of stochastic echo state networks, and therefore the class of all stochastic reservoir computers, are universal approximating classes. We also investigate the performance of two practical examples of stochastic reservoir computers in classification and chaotic time series prediction. While shot noise is a limiting factor in the performance of stochastic reservoir computing, we show significantly improved performance compared to a deterministic reservoir computer with similar hardware in cases where the effects of noise are small.

Key facts. Cited by 4 papers in the map (data through 13 Oct 2026). Builds on 16 of its 46 references that are in the map. First posted on arXiv 20 May 2024.

Builds on

16 of 46 references.

References · 16

  1. 2018Barren plateaus in quantum neural network training landscapescited by 627
  2. 2018Echo state networks are universalcited by 87
  3. 2017Failures of Gradient-Based Deep Learningcited by 79
  4. 2018Reservoir Computing Universality With Stochastic Inputscited by 48
  5. 2017Universal discrete-time reservoir computers with stochastic inputs and linear readouts using non-homogeneous state-affine systemscited by 39
  6. 2018Reservoir computing approaches for representation and classification of multivariate time seriescited by 38
  7. 2018Using a reservoir computer to learn chaotic attractors, with applications to chaos synchronisation and cryptographycited by 16
  8. 2018Rapid Time Series Prediction with a Hardware-Based Reservoir Computercited by 14
  9. 2019Learning Nonlinear Input-Output Maps with Dissipative Quantum Systemscited by 13
  10. 2023A full-stack view of probabilistic computing with p-bits: devices, architectures and algorithmscited by 13
  11. 2023Quantum-limited stochastic optical neural networks operating at a few quanta per activationcited by 8
  12. 2023Simple Cycle Reservoirs are Universalcited by 8
4 more
  1. 2020Large-scale spatiotemporal photonic reservoir computer for image classificationcited by 5
  2. 2022Universality and approximation bounds for echo state networks with random weightscited by 5
  3. 2021Nonlinear Autoregression with Convergent Dynamics on Novel Computational Platformscited by 3
  4. 2022Universal Time-Uniform Trajectory Approximation for Random Dynamical Systems with Recurrent Neural Networkscited by 1

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025Optical Echo State Network Reservoir Computingcited by 0
  2. 2025Reservoir-enhanced Segment Anything Model for Subsurface Diagnosiscited by 0
  3. 2025A Solvable Molecular Switch Model for Stable Temporal Information Processingcited by 0
  4. 2025Self-induced stochastic resonance: A physics-informed machine learning approachcited by 0