Statistical and Machine Learning forecasting methods: Concerns and ways forward

S Makridakis, E Spiliotis, V Assimakopoulos - PloS one, 2018 - journals.plos.org
Machine Learning (ML) methods have been proposed in the academic literature as
alternatives to statistical ones for time series forecasting. Yet, scant evidence is available …

Temporal data classification and forecasting using a memristor-based reservoir computing system

J Moon, W Ma, JH Shin, F Cai, C Du, SH Lee… - Nature Electronics, 2019 - nature.com
Time-series analysis including forecasting is essential in a range of fields from finance to
engineering. However, long-term forecasting is difficult, particularly for cases where the …

Physical reservoir computing—an introductory perspective

K Nakajima - Japanese Journal of Applied Physics, 2020 - iopscience.iop.org
Understanding the fundamental relationships between physics and its information-
processing capability has been an active research topic for many years. Physical reservoir …

A practical guide to applying echo state networks

M Lukoševičius - Neural Networks: Tricks of the Trade: Second Edition, 2012 - Springer
Reservoir computing has emerged in the last decade as an alternative to gradient descent
methods for training recurrent neural networks. Echo State Network (ESN) is one of the key …

Reservoir computing trends

M Lukoševičius, H Jaeger, B Schrauwen - KI-Künstliche Intelligenz, 2012 - Springer
Reservoir Computing (RC) is a paradigm of understanding and training Recurrent Neural
Networks (RNNs) based on treating the recurrent part (the reservoir) differently than the …

Embedding and approximation theorems for echo state networks

A Hart, J Hook, J Dawes - Neural Networks, 2020 - Elsevier
Abstract Echo State Networks (ESNs) are a class of single-layer recurrent neural networks
that have enjoyed recent attention. In this paper we prove that a suitable ESN, trained on a …

Investigating the accuracy of cross-learning time series forecasting methods

AA Semenoglou, E Spiliotis, S Makridakis… - International Journal of …, 2021 - Elsevier
The M4 competition identified innovative forecasting methods, advancing the theory and
practice of forecasting. One of the most promising innovations of M4 was the utilization of …

Scalable photonic platform for real-time quantum reservoir computing

J García-Beni, GL Giorgi, MC Soriano, R Zambrini - Physical Review Applied, 2023 - APS
Quantum reservoir computing (QRC) exploits the information-processing capabilities of
quantum systems to solve nontrivial temporal tasks, improving over their classical …

Echo state networks trained by Tikhonov least squares are L2 (μ) approximators of ergodic dynamical systems

AG Hart, JL Hook, JHP Dawes - Physica D: Nonlinear Phenomena, 2021 - Elsevier
Abstract Echo State Networks (ESNs) are a class of single-layer recurrent neural networks
with randomly generated internal weights, and a single layer of tuneable outer weights …

3D-integrated multilayered physical reservoir array for learning and forecasting time-series information

S Choi, J Shin, G Park, JS Eo, J Jang, JJ Yang… - Nature …, 2024 - nature.com
A wide reservoir computing system is an advanced architecture composed of multiple
reservoir layers in parallel, which enables more complex and diverse internal dynamics for …