A Differentiable Approach to Multi-scale Brain Modeling
This work provides a promising tool for neuroscientists to bridge data across electrophysiological, anatomical, and behavioral scales, though it appears incremental as it builds on existing differentiable simulation methods.
The paper tackled the problem of integrating neuroscience data across different scales by developing a multi-scale differentiable brain modeling workflow using BrainPy, achieving superior performance and speed in fitting single neuron models and successfully replicating neural activity and synaptic weight distributions in network models trained on cognitive tasks.
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.