Data-Driven Predictive Modeling of Neuronal Dynamics using Long Short-Term Memory

TL;DR

This paper introduces a novel LSTM-based data-driven model for predicting complex neuronal dynamics over extended time horizons, aiming to enhance brain modeling and control strategies.

Contribution

The study develops a unique LSTM architecture with a single output layer and reversed sequence mapping for improved long-term prediction accuracy of neuronal behaviors.

Findings

Successfully reconstructs spiking to bursting neuronal dynamics

Predicts multi-time scale neuronal activity with reasonable accuracy

Prediction accuracy improves with longer time horizons

Abstract

Modeling brain dynamics to better understand and control complex behaviors underlying various cognitive brain functions are of interests to engineers, mathematicians, and physicists from the last several decades. With a motivation of developing computationally efficient models of brain dynamics to use in designing control-theoretic neurostimulation strategies, we have developed a novel data-driven approach in a long short-term memory (LSTM) neural network architecture to predict the temporal dynamics of complex systems over an extended long time-horizon in future. In contrast to recent LSTM-based dynamical modeling approaches that make use of multi-layer perceptrons or linear combination layers as output layers, our architecture uses a single fully connected output layer and reversed-order sequence-to-sequence mapping to improve short time-horizon prediction accuracy and to make multi-timestep predictions of dynamical behaviors. We demonstrate the efficacy of our approach in reconstructing the regular spiking to bursting dynamics exhibited by an experimentally-validated 9-dimensional Hodgkin-Huxley model of hippocampal CA1 pyramidal neurons. Through simulations, we show that our LSTM neural network can predict the multi-time scale temporal dynamics underlying various spiking patterns with reasonable accuracy. Moreover, our results show that the predictions improve with increasing predictive time-horizon in the multi-timestep deep LSTM neural network.