Illuminating the black box of reservoir computing
Authors:
Open Access
- 19 May 2026
- journal article
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Abstract
Reservoir computers, using recurrent neural networks with fixed random connections, are known to perform a wide range of information-processing tasks. Yet the transformations taking place within the reservoir, the interaction between input matrix, reservoir, and readout layer, and the influence of key design parameters remain insufficiently understood. Here, we shift the focus from performance maximization to the identification of minimal computational requirements for different model tasks. We investigate how many neurons and how much nonlinearity are needed to solve specific tasks, including cases with non-sigmoidal activation functions. Our results show that the division of labor between input matrix, reservoir, and readout layer depends strongly on the task. In many cases, a weakly coupled and only minimally nonlinear reservoir proves sufficient. In addition, features often considered secondary, such as the structure of the input matrix or the steepness of the activation functions, can become decisive for performance.Keywords
All Related Versions
Funding Information
- Friedrich-Alexander-Universität Erlangen-Nürnberg
This publication has 46 references indexed in Scilit:
- Fading memory echo state networks are universalNeural Networks, 2021
- The stochastic resonance model of auditory perception: A unified explanation of tinnitus development, Zwicker tone illusion, and residual inhibition2021
- Sparsity through evolutionary pruning prevents neuronal networks from overfittingNeural Networks, 2020
- Effect of dilution in asymmetric recurrent neural networksNeural Networks, 2018
- Noise-modulated neural networks as an application of stochastic resonanceNeurocomputing, 2018
- Recurrent neural networks as versatile tools of neuroscience researchCurrent Opinion in Neurobiology, 2017
- Is cortical connectivity optimized for storing information?Nature Neuroscience, 2016
- What are Extreme Learning Machines? Filling the Gap Between Frank Rosenblatt’s Dream and John von Neumann’s PuzzleCognitive Computation, 2015
- Recurrent Neural Networks Are Universal Approximators2006
- Dale’s principleBrain Research Bulletin, 1999