Perturbing a Neural Network to Infer Effective Connectivity: Evidence from Synthetic EEG Data

TL;DR

This paper introduces a data-driven method using neural network perturbations to infer effective brain connectivity from EEG data, outperforming classical methods on synthetic datasets.

Contribution

It proposes a novel framework that leverages neural network perturbations to identify causal relationships in EEG signals, demonstrating improved performance over traditional approaches.

Findings

CNN and Transformer models outperform classical Granger causality.

The method accurately infers causal links in synthetic EEG data.

Neural network perturbation reveals underlying effective connectivity.

Abstract

Identifying causal relationships among distinct brain areas, known as effective connectivity, holds key insights into the brain's information processing and cognitive functions. Electroencephalogram (EEG) signals exhibit intricate dynamics and inter-areal interactions within the brain. However, methods for characterizing nonlinear causal interactions among multiple brain regions remain relatively underdeveloped. In this study, we proposed a data-driven framework to infer effective connectivity by perturbing the trained neural networks. Specifically, we trained neural networks (i.e., CNN, vanilla RNN, GRU, LSTM, and Transformer) to predict future EEG signals according to historical data and perturbed the networks' input to obtain effective connectivity (EC) between the perturbed EEG channel and the rest of the channels. The EC reflects the causal impact of perturbing one node on others. The performance was tested on the synthetic EEG generated by a biological-plausible Jansen-Rit model. CNN and Transformer obtained the best performance on both 3-channel and 90-channel synthetic EEG data, outperforming the classical Granger causality method. Our work demonstrated the potential of perturbing an artificial neural network, learned to predict future system dynamics, to uncover the underlying causal structure.