Statistical and Machine Learning forecasting methods: Concerns and ways forward
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 …
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
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 …
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 …
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 …
methods for training recurrent neural networks. Echo State Network (ESN) is one of the key …
Reservoir computing trends
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 …
Networks (RNNs) based on treating the recurrent part (the reservoir) differently than the …
Embedding and approximation theorems for echo state networks
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 …
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
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 …
practice of forecasting. One of the most promising innovations of M4 was the utilization of …
Scalable photonic platform for real-time quantum reservoir computing
Quantum reservoir computing (QRC) exploits the information-processing capabilities of
quantum systems to solve nontrivial temporal tasks, improving over their classical …
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
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 …
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
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 …
reservoir layers in parallel, which enables more complex and diverse internal dynamics for …