Identifying nonlinear dynamical systems via generative recurrent neural networks with applications to fMRI

Abstract

A major tenet in theoretical neuroscience is that cognitive and behavioral processes are ultimately implemented in terms of the neural system dynamics. Accordingly, a major aim for the analysis of neurophysiological measurements should lie in the identification of the computational dynamics underlying task processing. Here we advance a state space model (SSM) based on generative piecewise-linear recurrent neural networks (PLRNN) to assess dynamics from neuroimaging data. In contrast to many other nonlinear time series models which have been proposed for reconstructing latent dynamics, our model is easily interpretable in neural terms, amenable to systematic dynamical systems analysis of the resulting set of equations, and can straightforwardly be transformed into an equivalent continuous-time dynamical system. The major contributions of this paper are the introduction of a new observation model suitable for functional magnetic resonance imaging (fMRI) coupled to the latent PLRNN, an efficient stepwise training procedure that forces the latent model to capture the 'true' underlying dynamics rather than just fitting (or predicting) the observations, and of an empirical measure based on the Kullback-Leibler divergence to evaluate from empirical time series how well this goal of approximating the underlying dynamics has been achieved. We validate and illustrate the power of our approach on simulated 'ground-truth' dynamical (benchmark) systems as well as on actual experimental fMRI time series, and demonstrate that the latent dynamics harbors task-related nonlinear structure that a linear dynamical model fails to capture. Given that fMRI is one of the most common techniques for measuring brain activity non-invasively in human subjects, this approach may provide a novel step toward analyzing aberrant (nonlinear) dynamics for clinical assessment or neuroscientific research.

References in corpus (13)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• A survey of cross-validation procedures for model selection
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• A Recurrent Latent Variable Model for Sequential Data
• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• Curse-of-dimensionality revisited: Collapse of the particle filter in very large scale systems
• Fighting Sample Degeneracy and Impoverishment in Particle Filters: A Review of Intelligent Approaches
• Learning Stochastic Recurrent Networks
• Black box variational inference for state space models
• Improving performance of recurrent neural network with relu nonlinearity
• Approximate Methods for State-Space Models
• A State Space Approach for Piecewise-Linear Recurrent Neural Networks for Reconstructing Nonlinear Dynamics from Neural Measurements
• Variational online learning of neural dynamics

Cited by in corpus (5)

• Identifying nonlinear dynamical systems with multiple time scales and long-range dependencies
• Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems
• From reductionism to realism: Holistic mathematical modelling for complex biological systems
• Time-Reversal Symmetric ODE Network
• Physics-based polynomial neural networks for one-shot learning of dynamical systems from one or a few samples