Next Generation Reservoir Computing

06/14/2021
by   Daniel J. Gauthier, et al.
0

Reservoir computing is a best-in-class machine learning algorithm for processing information generated by dynamical systems using observed time-series data. Importantly, it requires very small training data sets, uses linear optimization, and thus requires minimal computing resources. However, the algorithm uses randomly sampled matrices to define the underlying recurrent neural network and has a multitude of metaparameters that must be optimized. Recent results demonstrate the equivalence of reservoir computing to nonlinear vector autoregression, which requires no random matrices, fewer metaparameters, and provides interpretable results. Here, we demonstrate that nonlinear vector autoregression excels at reservoir computing benchmark tasks and requires even shorter training data sets and training time, heralding the next generation of reservoir computing.

READ FULL TEXT
research
07/28/2022

Learning unseen coexisting attractors

Reservoir computing is a machine learning approach that can generate a s...
research
06/11/2020

Model-Size Reduction for Reservoir Computing by Concatenating Internal States Through Time

Reservoir computing (RC) is a machine learning algorithm that can learn ...
research
01/23/2023

Learning Reservoir Dynamics with Temporal Self-Modulation

Reservoir computing (RC) can efficiently process time-series data by tra...
research
12/13/2021

Interpretable Design of Reservoir Computing Networks using Realization Theory

The reservoir computing networks (RCNs) have been successfully employed ...
research
01/13/2022

`Next Generation' Reservoir Computing: an Empirical Data-Driven Expression of Dynamical Equations in Time-Stepping Form

Next generation reservoir computing based on nonlinear vector autoregres...
research
06/02/2017

Reservoir Computing for Detection of Steady State in Performance Tests of Compressors

Fabrication of devices in industrial plants often includes undergoing qu...
research
07/07/2023

Controlling Chaotic Maps using Next-Generation Reservoir Computing

In this work, we combine nonlinear system control techniques with next-g...

Please sign up or login with your details

Forgot password? Click here to reset