Pith. sign in

REVIEW 5 cited by

Deep Echo State Network (DeepESN): A Brief Survey

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1712.04323 v4 pith:RK56CGXE submitted 2017-12-12 cs.LG cs.AIstat.ML

Claudio Gallicchio , Alessio Micheli This is my paper · ORCID
classification cs.LGcs.AIstat.ML
keywords deepnetworksneuralstatedeepesndeepesnsechonetwork
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The study of deep recurrent neural networks (RNNs) and, in particular, of deep Reservoir Computing (RC) is gaining an increasing research attention in the neural networks community. The recently introduced Deep Echo State Network (DeepESN) model opened the way to an extremely efficient approach for designing deep neural networks for temporal data. At the same time, the study of DeepESNs allowed to shed light on the intrinsic properties of state dynamics developed by hierarchical compositions of recurrent layers, i.e. on the bias of depth in RNNs architectural design. In this paper, we summarize the advancements in the development, analysis and applications of DeepESNs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Predicting Critical Transitions in Multiscale Dynamical Systems Using Reservoir Computing

    physics.comp-ph 2019-08 conditional novelty 6.0 of 10

    A reservoir-computing pipeline that extracts and predicts the fast forcing from slow-variable data can forecast rare critical transitions ahead of time in slow-fast dynamical systems.

  2. Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking

    cs.LG 2026-02 conditional novelty 5.0 of 10

    Echo State Networks match or beat ARIMA and TBATS on quarterly M4 series and match them on monthly series while using less compute after an extensive hyperparameter sweep.

  3. From Neurons to Computation: Biological Reservoir Computing for Pattern Recognition

    cs.NE 2025-05 conditional novelty 4.0 of 10

    Cultured neurons on a 4096-electrode array act as a biological reservoir, and a linear classifier reading their spike counts reaches 92-98% accuracy on three simple pattern-recognition tasks.

  4. Dissipation-induced Quantum Homogenization for Temporal Information Processing

    quant-ph 2024-12 reject novelty 4.0 of 10

    The authors argue the disordered quantum homogenizer is a viable reservoir computer because its dissipative dynamics converge to a steady state, but the proof is incomplete.

  5. Recurrent Stochastic Configuration Networks with Incremental Blocks

    cs.LG 2024-11 reject novelty 4.0 of 10

    Block RSCN adds reservoir nodes in blocks and claims universal approximation, echo state, and online convergence.

Pith tools