Illuminating the black box of reservoir computing.

Overview

1. Cognitive Computational Neuroscience Group, Pattern Recognition Lab, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Erlangen, Germany
2. Mannheim Center for Neuromodulation and Neuroprosthetics (MCNN), University Hospital Mannheim, University Heidelberg, Heidelberg, Germany
3. Neuroscience Lab, University Hospital Erlangen, Erlangen, Germany

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.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper says that its authors' code is available on request: it was not published with the paper, so there is nothing to verify.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none (its code is available on request), so it has no map.

Data

No dataset and no data link were found in the paper.

Data availability

The complete data and analysis programs will be made available upon reasonable request.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 2, 28 September 2026

• Funding: added Friedrich-Alexander-Universität Erlangen-Nürnberg

Version 1, 28 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 5 authors, 4 keywords, 35 references.

Cite

This paper

Metzner, C., Kinfe, T., Maier, A., Schilling, A., & Krauss, P. (2026). Illuminating the black box of reservoir computing. Scientific reports, 16(1), 15500. https://doi.org/10.1038/s41598-026-53098-y

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1038/s41467-026-74466-2 [code]

Neuromorphic hierarchical modular reservoirs.

Journal: Nature communications

In common: 5 references

[2] doi:10.1007/s11571-026-10512-5 [code]

Modeling the rhythmic complexity of professional drumming with an oscillation-driven reservoir computer.

Journal: Cognitive neurodynamics

In common: 3 references

[3] doi:10.3389/fncom.2026.1761735 [code]

Adaptation modulates effective connectivity and network stability.

Journal: Frontiers in computational neuroscience

In common: 3 references

[4] doi:10.1126/sciadv.aec3893 [code]

Enriched experience increases reciprocal synaptic connectivity and coding sparsity in higher-order cortex.

Journal: Science advances

In common: 3 references

[5] doi:10.1038/s41467-026-71914-x [code]

Developmental emergence of sparse and structured synaptic connectivity in the hippocampal CA3 memory circuit.

Journal: Nature communications

In common: 3 references

[6] doi:10.1038/s42003-026-09938-8 [code]

Representation Transfer via Invariant Input-driven Continuous Attractors for Fast Domain Adaptation.

Journal: Communications biology

In common: 3 references

[7] doi:10.1038/s41598-026-41532-0 [code]

Prediction, syntax and semantic grounding in the brain and large language models.

Journal: Scientific reports

In common: 2 references

[8] doi:10.1016/j.neuron.2026.07.016 [code]

Inferring brain-wide interactions using data-constrained recurrent neural network models.

Journal: Neuron

In common: 2 references

[9] doi:10.1016/j.isci.2026.116144 [code]

Spatial continuity of neurons explains non-random network architecture.

Journal: iScience

In common: 2 references

[10] doi:10.1371/journal.pcbi.1014730 [code]

A unified model of short- and long-term plasticity: Effects on network connectivity and information capacity.

Journal: PLoS computational biology

In common: 2 references

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.