Necessary and Sufficient Reservoir Condition for Universal Reservoir Computing
Open Access
- 28 October 2025
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 13 (21) , 3440
Abstract
We discuss necessary and sufficient conditions for universal approximation using reservoir computing. Reservoir computing is a machine learning method used to train a dynamical system model by tuning only the static part of the model. The universality is the ability of the model to approximate any dynamical system with any precision. In the previous studies, we provided two sufficient conditions for the universality. We employed the universality definition that has been discussed since the earliest studies on reservoir computing. In this present paper, we prove that these two conditions and the universality are equivalent to one another. Using this equivalence, we show that a universal model must have a “pathological” property that can only be achieved or approached by chaotic reservoirs.Keywords
Funding Information
- Japan Society for the Promotion of Science (JP25K03203)
This publication has 21 references indexed in Scilit:
- Iono–Magnonic Reservoir Computing With Chaotic Spin Wave Interference Manipulated by Ion‐GatingAdvanced Science, 2024
- Existence of reservoir with finite-dimensional output for universal reservoir computingScientific Reports, 2024
- A perspective on physical reservoir computing with nanomagnetic devicesApplied Physics Letters, 2023
- FPGA-based Reservoir Computing with Optimized Reservoir Node Architecture2022
- Reservoir Computing2021
- Reservoir computing based on quenched chaosChaos, Solitons & Fractals, 2020
- Recent advances in physical reservoir computing: A reviewNeural Networks, 2019
- Neuromorphic computing with nanoscale spintronic oscillatorsNature, 2017
- Reservoir computing approaches to recurrent neural network trainingComputer Science Review, 2009
- An experimental unification of reservoir computing methodsNeural Networks, 2007