The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Echo State Property Linked to an Input: Exploring a Fundamental Characteristic of Recurrent Neural Networks
Abstract
The echo state property is a key for the design and training of recurrent neural networks within the paradigm of reservoir computing. In intuitive terms, this is a passivity condition: a network having this property, when driven by an input signal, will become entrained by the input and develop an internal response signal. This excited internal dynamics can be seen as a high-dimensional, nonlinear, unique transform of the input with a rich memory content. This view has implications for understanding neural dynamics beyond the field of reservoir computing. Available definitions and theorems concerning the echo state property, however, are of little practical use because they do not relate the network response to temporal or statistical properties of the driving input. Here we present a new definition of the echo state property that directly connects it to such properties. We derive a fundamental 0-1 law: if the input comes from an ergodic source, the network response has the echo state property with probability one or zero, independent of the given network. Furthermore, we give a sufficient condition for the echo state property that connects statistical characteristics of the input to algebraic properties of the network connection matrix. The mathematical methods that we employ are freshly imported from the young field of nonautonomous dynamical systems theory. Since these methods are not yet well known in neural computation research, we introduce them in some detail. As a side story, we hope to demonstrate the eminent usefulness of these methods.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Maass, W., Natschläger, T., & Markram, H. (2002) · Neural Computation · doi:10.1162/089976602760407955 · Cited by 4,025 · cited 1×
“ESNs are artificial recurrent neural networks (RNNs) which are used in machine learning for the supervised training of temporal pattern recognizers, pattern generators, predictors, controllers and more (short overview: [12]; target paper: [10]; survey on state of the art: [16]; other RC flavors besides ESNs: liquid st…”
BackgroundHarnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication
Jaeger, H., & Haas, H. (2004) · Science · doi:10.1126/science.1091277 · Cited by 3,811
Self-citationReservoir computing approaches to recurrent neural network training
Lukoševičius, M., & Jaeger, H. (2009) · Computer Science Review · doi:10.1016/j.cosrev.2009.03.005 · Cited by 2,956
Self-citationOptimization and applications of echo state networks with leaky- integrator neurons
Jaeger, H., Lukoševičius, M., Popovici, D., & Siewert, U. (2007) · Neural Networks · doi:10.1016/j.neunet.2007.04.016 · Cited by 948
Self-citationNeural circuits as computational dynamical systems
Sussillo, D. (2014) · Current Opinion in Neurobiology · doi:10.1016/j.conb.2014.01.008 · Cited by 247
Cited by
Jaeger, H. (2007) · Scholarpedia · doi:10.4249/scholarpedia.2330 · Cited by 459
Self-citationPhysical reservoir computing—an introductory perspective
Nakajima, K. (2020) · Japanese Journal of Applied Physics · doi:10.35848/1347-4065/ab8d4f · Cited by 422
Randomness in neural networks: an overview
Scardapane, S., & Wang, D. (2017) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1200 · Cited by 352
Echo state networks are universal
Grigoryeva, L., & Ortega, J.-P. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.08.025 · Cited by 274
Neural circuits as computational dynamical systems
Sussillo, D. (2014) · Current Opinion in Neurobiology · doi:10.1016/j.conb.2014.01.008 · Cited by 247
Metadata
- Authors
- Manjunath, G., & Jaeger, H.
- Venue
- Neural Computation
- Publisher
- MIT Press - Journals
- Published
- 2013-03
- Volume
- 25
- Issue
- 3
- Pages
- 671-696
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2148520247
- Cited by
- 222
- References
- 5
- FWCI
- 6.65
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.