mlsanityData to 7 Oct 2026

Master memory function for delay-based reservoir computers with single-variable dynamics

arXiv 2108.12643 ↗First posted 28 Aug 2021cs.ET cs.LG nlin.AOcited by 3

Not on the map. Why?

Abstract (arXiv)

We show that many delay-based reservoir computers considered in the literature can be characterized by a universal master memory function (MMF). Once computed for two independent parameters, this function provides linear memory capacity for any delay-based single-variable reservoir with small inputs. Moreover, we propose an analytical description of the MMF that enables its efficient and fast computation. Our approach can be applied not only to reservoirs governed by known dynamical rules such as Mackey-Glass or Ikeda-like systems but also to reservoirs whose dynamical model is not available. We also present results comparing the performance of the reservoir computer and the memory capacity given by the MMF.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 18 of its 91 references that are in the map. First posted on arXiv 28 Aug 2021.

Builds on

18 of 91 references.

References · 18

  1. 2021Next Generation Reservoir Computingcited by 160
  2. 2018Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Modelcited by 57
  3. 2018Reservoir Computing Universality With Stochastic Inputscited by 48
  4. 2017Reinforcement Learning in a large scale photonic Recurrent Neural Networkcited by 30
  5. 2020Combining Machine Learning with Knowledge-Based Modeling for Scalable Forecasting and Subgrid-Scale Closure of Large, Complex, Spatiotemporal Systemscited by 23
  6. 2021Model-free inference of unseen attractors: Reconstructing phase space features from a single noisy trajectory using reservoir computingcited by 21
  7. 2020Human action recognition with a large-scale brain-inspired photonic computercited by 15
  8. 2020Deep Time-Delay Reservoir Computing: Dynamics and Memory Capacitycited by 10
  9. 2020Deep Neural Networks using a Single Neuron: Folded-in-Time Architecture using Feedback-Modulated Delay Loopscited by 9
  10. 2016Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalisationcited by 6
  11. 2019Performance boost of time-delay reservoir computing by non-resonant clock cyclecited by 6
  12. 2020A complete, parallel and autonomous photonic neural network in a semiconductor multimode lasercited by 6
6 more
  1. 2021Performance and Complexity Analysis of bi-directional Recurrent Neural Network Models vs. Volterra Nonlinear Equalizers in Digital Coherent Systemscited by 6
  2. 2017Photonic machine learning implementation for signal recovery in optical communicationscited by 4
  3. 2018Reservoir computing with simple oscillators: Virtual and real networkscited by 3
  4. 2019Richness of Deep Echo State Network Dynamicscited by 3
  5. 2019Takens-inspired neuromorphic processor: a downsizing tool for random recurrent neural networks via feature extractioncited by 3
  6. 2020Limitations of the recall capabilities in delay based reservoir computing systemscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Adaptive Sensing of Continuous Physical Systems for Machine Learningcited by 0
  2. 2026Information Processing Capacity of Stationary Physical Systems: Theory, Data-efficient Estimation Methods, and Photonic Demonstrationcited by 0
  3. 2026Inference of Unknown Dynamical Components Using Next Generation Reservoir Computing: From Chaotic Systems to Climate Datacited by 0