Short note on the behavior of recurrent neural network for noisy dynamical system

Abstract

The behavior of recurrent neural network for the data-driven simulation of noisy dynamical systems is studied by training a set of Long Short-Term Memory Networks (LSTM) on the Mackey-Glass time series with a wide range of noise level. It is found that, as the training noise becomes larger, LSTM learns to depend more on its autonomous dynamics than the noisy input data. As a result, LSTM trained on noisy data becomes less susceptible to the perturbation in the data, but has a longer relaxation timescale. On the other hand, when trained on noiseless data, LSTM becomes extremely sensitive to a small perturbation, but is able to adjusts to the changes in the input data.

References in corpus (2)

• Deep learning for universal linear embeddings of nonlinear dynamics
• Deep learning algorithm for data-driven simulation of noisy dynamical system

Cited by in corpus (6)

• A non-intrusive reduced order modeling framework for quasi-geostrophic turbulence
• Data-driven Reconstruction of Nonlinear Dynamics from Sparse Observation
• A fast noise filtering algorithm for time series prediction using recurrent neural networks
• Impact of Medical Data Imprecision on Learning Results
• Variational inference formulation for a model-free simulation of a dynamical system with unknown parameters by a recurrent neural network
• Deep Chaos Synchronization