Ultrafast large-scale simulations of biophysically realistic neurons using deep learning

Abstract

Understanding the activity of the mammalian brain requires an integrative knowledge of circuits at distinct scales, ranging from ion channel gating to circuit connectomics. To understand how multiple parameters contribute synergistically to circuit behavior, neuronal computational models are regularly employed. However, traditional models containing anatomically and biophysically realistic neurons are computationally demanding even when scaled to model local circuits. To overcome this limitation, we trained several artificial neural net (ANN) architectures to model the activity of realistic, multicompartmental neurons. We identified a single ANN that accurately predicted both subthreshold and action potential firing and correctly generalized its responses to previously unobserved synaptic input. When scaled, processing times were orders of magnitude faster compared with traditional approaches, allowing for rapid parameter-space mapping in a circuit model of Rett syndrome. Thus, we present a novel ANN approach that allows for rapid, detailed network experiments using inexpensive, readily available computational resources.