Data-driven modelling of brain activity using neural networks, Diffusion Maps, and the Koopman operator

Abstract

We propose a machine-learning approach to model long-term out-of-sample dynamics of brain activity from task-dependent fMRI data. Our approach is a three stage one. First, we exploit Diffusion maps (DMs) to discover a set of variables that parametrize the low-dimensional manifold on which the emergent high-dimensional fMRI time series evolve. Then, we construct reduced-order-models (ROMs) on the embedded manifold via two techniques: Feedforward Neural Networks (FNNs) and the Koopman operator. Finally, for predicting the out-of-sample long-term dynamics of brain activity in the ambient fMRI space, we solve the pre-image problem coupling DMs with Geometric Harmonics (GH) when using FNNs and the Koopman modes per se. For our illustrations, we have assessed the performance of the two proposed schemes using a benchmark fMRI dataset with recordings during a visuo-motor task. The results suggest that just a few (for the particular task, five) non-linear coordinates of the high-dimensional fMRI time series provide a good basis for modelling and out-of-sample prediction of the brain activity. Furthermore, we show that the proposed approaches outperform the one-step ahead predictions of the naive random walk model, which, in contrast to our scheme, relies on the knowledge of the signals in the previous time step. Importantly, we show that the proposed Koopman operator approach provides, for any practical purposes, equivalent results to the FNN-GH approach, thus bypassing the need to train a non-linear map and to use GH to extrapolate predictions in the ambient fMRI space; one can use instead the low-frequency truncation of the DMs function space of L^2-integrable functions, to predict the entire list of coordinate functions in the fMRI space and to solve the pre-image problem.

References in corpus (19)

• Scikit-learn: Machine Learning in Python
• A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition
• Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control
• Applied Koopmanism
• Koopman invariant subspaces and finite linear representations of nonlinear dynamical systems for control
• Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
• Extended dynamic mode decomposition with dictionary learning: a data-driven adaptive spectral decomposition of the Koopman operator
• Chimera Death: Symmetry Breaking in Dynamical Networks
• Higher-order interactions in complex networks of phase oscillators promote abrupt synchronization switching
• Intrinsic dimension of data representations in deep neural networks
• Coarse-scale PDEs from fine-scale observations via machine learning
• Exact neural mass model for synaptic-based working memory
• Reduced models in chemical kinetics via nonlinear data-mining
• Constructing coarse-scale bifurcation diagrams from spatio-temporal observations of microscopic simulations: A parsimonious machine learning approach
• Nonlinear Intrinsic Variables and State Reconstruction in Multiscale Simulations
• On the Koopman operator of algorithms
• Time Series Forecasting Using Manifold Learning
• Data-driven Control of Agent-based Models: an Equation/Variable-free Machine Learning Approach
• Double Diffusion Maps and their Latent Harmonics for Scientific Computations in Latent Space

Cited by in corpus (4)

• RandONet: Shallow-Networks with Random Projections for learning linear and nonlinear operators
• A physics-informed neural network method for the approximation of slow invariant manifolds for the general class of stiff systems of ODEs
• Learning the Latent dynamics of Fluid flows from High-Fidelity Numerical Simulations using Parsimonious Diffusion Maps
• Early warning indicators via latent stochastic dynamical systems