A Differentiable Approach to Multi-scale Brain Modeling

TL;DR

This paper introduces a multi-scale differentiable brain modeling workflow using BrainPy, enabling gradient-based optimization across neuron, network, and behavior levels, improving model fitting and biological plausibility.

Contribution

It presents a novel differentiable simulation framework that integrates electrophysiological, anatomical, and behavioral data for comprehensive brain modeling.

Findings

Achieved superior performance in fitting neuron models.

Successfully replicated neural activity and synaptic distributions in cognitive tasks.

Demonstrated efficient gradient-based optimization across multiple brain scales.

Abstract

We present a multi-scale differentiable brain modeling workflow utilizing BrainPy, a unique differentiable brain simulator that combines accurate brain simulation with powerful gradient-based optimization. We leverage this capability of BrainPy across different brain scales. At the single-neuron level, we implement differentiable neuron models and employ gradient methods to optimize their fit to electrophysiological data. On the network level, we incorporate connectomic data to construct biologically constrained network models. Finally, to replicate animal behavior, we train these models on cognitive tasks using gradient-based learning rules. Experiments demonstrate that our approach achieves superior performance and speed in fitting generalized leaky integrate-and-fire and Hodgkin-Huxley single neuron models. Additionally, training a biologically-informed network of excitatory and inhibitory spiking neurons on working memory tasks successfully replicates observed neural activity and synaptic weight distributions. Overall, our differentiable multi-scale simulation approach offers a promising tool to bridge neuroscience data across electrophysiological, anatomical, and behavioral scales.