paper-with-me

Papers

Bidirectional deep-readout echo state networks

2017-11-17 · Filippo Maria Bianchi, Simone Scardapane, Sigurd Løkse, Robert Jenssen

We propose a deep architecture for the classification of multivariate time series. By means of a recurrent and untrained reservoir we generate a vectorial representation that embeds temporal relationships in the data. To improve the memorization capability, we implement a bidirectional reservoir, whose last state captures also past dependencies in the input. We apply dimensionality reduction to the final reservoir states to obtain compressed fixed size representations of the time series. These are subsequently fed into a deep feedforward network trained to perform the final classification. We test our architecture on benchmark datasets and on a real-world use-case of blood samples classification. Results show that our method performs better than a standard echo state network and, at the same time, achieves results comparable to a fully-trained recurrent network, but with a faster training.

📄 PDF Abstract BibTeX arXiv:1711.06509

Code (2)

FilippoMB/Bidirectional-Deep-Echo-State-Network 공식 구현 tf
FilippoMB/Bidirectional-Deep-reservoir-Echo-State-Network 공식 구현 tf

Tasks

ClassificationDimensionality ReductionGeneral ClassificationMemorizationTime SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

Model-Coupled Autoencoder for Time Series Visualisation

2016-01-21 · Nikolaos Gianniotis, Sven D. Kügler, Peter Tiňo, Kai L. Polsterer

We present an approach for the visualisation of a set of time series that combines an echo state network with an autoencoder. For each time series in the dataset we train an echo state network, using a common and fixed r…

Dimensionality ReductionmodelTime SeriesTime Series Analysis

Discovering Dynamical Parameters by Interpreting Echo State Networks

2021-09-24 · NeurIPS Workshop AI4Scien 2021 12 · Oreoluwa Alao, Peter Y Lu, Marin Soljacic

Reservoir computing architectures known as echo state networks (ESNs) have been shown to have exceptional predictive capabilities when trained on chaotic systems. However, ESN models are often seen as black-box predictor…

Unsupervised Learning in Echo State Networks for Input Reconstruction

2025-01-20 · Taiki Yamada, Yuichi Katori, Kantaro Fujiwara

Conventional echo state networks (ESNs) require supervised learning to train the readout layer, using the desired outputs as training data. In this study, we focus on input reconstruction (IR), which refers to training t…

Time Series

Echo State Networks as State-Space Models: A Systems Perspective

2025-09-04 · Pradeep Singh, Balasubramanian Raman arxiv

Echo State Networks (ESNs) are typically presented as efficient, readout-trained recurrent models, yet their dynamics and design are often guided by heuristics rather than first principles. We recast ESNs explicitly as s…

Universality and approximation bounds for echo state networks with random weights

2022-06-12 · Zhen Li, Yunfei Yang

We study the uniform approximation of echo state networks with randomly generated internal weights. These models, in which only the readout weights are optimized during training, have made empirical success in learning d…