Switching Dynamical Systems with Deep Neural Networks

The problem of uncovering different dynamical regimes is of pivotal importance in time series analysis. Switching dynamical systems provide a solution for modeling physical phenomena whose time series data exhibit different dynamical modes. In this work we propose a novel variational RNN model for switching dynamics allowing for both non-Markovian and non-linear dynamical behavior between and within dynamic modes. Attention mechanisms are provided to inform the switching distribution.