Backpropagation on Dynamical Networks

Abstract

Dynamical networks are versatile models that can describe a variety of behaviours such as synchronisation and feedback. However, applying these models in real world contexts is difficult as prior information pertaining to the connectivity structure or local dynamics is often unknown and must be inferred from time series observations of network states. Additionally, the influence of coupling interactions between nodes further complicates the isolation of local node dynamics. Given the architectural similarities between dynamical networks and recurrent neural networks (RNN), we propose a network inference method based on the backpropagation through time (BPTT) algorithm commonly used to train recurrent neural networks. This method aims to simultaneously infer both the connectivity structure and local node dynamics purely from observation of node states. An approximation of local node dynamics is first constructed using a neural network. This is alternated with an adapted BPTT algorithm to regress corresponding network weights by minimising prediction errors of the dynamical network based on the previously constructed local models until convergence is achieved. This method was found to be succesful in identifying the connectivity structure for coupled networks of Lorenz, Chua and FitzHugh-Nagumo oscillators. Freerun prediction performance with the resulting local models and weights was found to be comparable to the true system with noisy initial conditions. The method is also extended to non-conventional network couplings such as asymmetric negative coupling.

References in corpus (18)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Chimera States for Coupled Oscillators
• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• Attractor Reconstruction by Machine Learning
• Data Based Identification and Prediction of Nonlinear and Complex Dynamical Systems
• Discovering Symbolic Models from Deep Learning with Inductive Biases
• Inferring Network Topology from Complex Dynamics
• Model-free inference of direct network interactions from nonlinear collective dynamics
• Autonomous inference of complex network dynamics from incomplete and noisy data
• Good and bad predictions: Assessing and improving the replication of chaotic attractors by means of reservoir computing
• Using Machine Learning to Assess Short Term Causal Dependence and Infer Network Links
• Model reconstruction from temporal data for coupled oscillator networks
• Reconstructing Network Dynamics of Coupled Discrete Chaotic Units from Data
• Machine Learning Link Inference of Noisy Delay-coupled Networks with Opto-Electronic Experimental Tests
• Inferring Causal Networks of Dynamical Systems through Transient Dynamics and Perturbation
• Revealing dynamics, communities and criticality from data
• Inferring a network from dynamical signals at its nodes
• Recovering sparse networks: Basis adaptation and stability under extensions