Learning dynamical systems in noise using convolutional neural networks

The problem of distinguishing deterministic chaos from non-chaotic dynamics has been an area of active research in time series analysis. Since noise contamination is unavoidable, it renders deterministic chaotic dynamics corrupted by noise to appear in close resemblance to stochastic dynamics. As a result, the problem of distinguishing noise-corrupted chaotic dynamics from randomness based on observations without access to the measurements of the state variables is difficult. We propose a new angle to tackle this problem by formulating it as a multi-class classification task. The task of classification involves allocating the observations/measurements to the unknown state variables in order to find the nature of these unobserved internal state variables. We employ signal and image processing based methods to characterize the different system dynamics. A deep learning technique using a state-of-the-art image classifier known as the Convolutional Neural Network (CNN) is designed to learn the dynamics. The time series are transformed into textured images of spectrogram and unthresholded recurrence plot (UTRP) for learning stochastic and deterministic chaotic dynamical systems in noise. We have designed a CNN that learns the dynamics of systems from the joint representation of the textured patterns from these images, thereby solving the problem as a pattern recognition task. The robustness and scalability of our approach is evaluated at different noise levels. Our approach demonstrates the advantage of applying the dynamical properties of chaotic systems in the form of joint representation of UTRP images along with spectrogram to improve learning dynamical systems in colored noise.