Neural Echo State Network using oscillations of gas bubbles in water
arXiv:2112.11592 · doi:10.1103/PhysRevE.105.044206
Abstract
In the framework of physical reservoir computing (RC), machine learning algorithms designed for digital computers are executed using analog computer-like nonlinear physical systems that can provide energy-efficient computational power for predicting time-dependent quantities that can be found using nonlinear differential equations. We suggest a bubble-based RC (BRC) system that combines the nonlinearity of an acoustic response of a cluster of oscillating gas bubbles in water with a standard Echo State Network (ESN) algorithm that is well-suited to forecast chaotic time series. We confirm the plausibility of the BRC system by numerically demonstrating its ability to forecast certain chaotic time series similarly to or even more accurately than ESN.
arXiv comment5 pages, 3 figures
References in corpus (13)
- Recent Advances in Physical Reservoir Computing: A Review
- Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
- Next Generation Reservoir Computing
- Physical reservoir computing -- An introductory perspective
- Harnessing disordered quantum dynamics for machine learning
- Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM
- Macromagnetic simulation for reservoir computing utilizing spin dynamics in magnetic tunnel junctions
- Computing with Networks of Nonlinear Mechanical Oscillators
- Reservoir computing using a spin-wave delay line active ring resonator
- Temporal pattern recognition with delayed feedback spin-torque nano-oscillators
- Performing Mathematical Operations using High-Index Acoustic Metamaterials
- Efficient implementations of echo state network cross-validation
- Spectrally-wide acoustic frequency combs generated using oscillations of polydisperse gas bubble clusters in liquids