From Hodgkin-Huxley to Pretrained Neural Inference AI
TL;DR
By pre-training artificial neural networks exclusively on large-scale synthetic data, this work demonstrates robust zero-shot generalization across diverse brain regions, experimental paradigms and species, enabling the accurate inference of single-unit activities and cell-type properties without exposure to real data.
Abstract
High-density probes record from thousands of neurons simultaneously, yet resolving single-neuron identity remains an illposed inverse problem. While detailed simulations precisely characterize the biophysical forward process, their utility for interpreting brain signal remains unclear. Here we show that biophysical simulations of population neuronal electrical signals serve as an effective bridge between theory and experiment. By pre-training artificial neural networks exclusively on large-scale synthetic data, we demonstrate robust zero-shot generalization across diverse brain regions, experimental paradigms and species, enabling the accurate inference of single-unit activities and cell-type properties without exposure to real data. Further-more, uncovering a substantial population of functionally competent but weakly active neurons systematically obscured by conventional heuristics, our framework resolves a long-standing discrepancy regarding ocular dominance in mouse primary visual cortex. These findings establish biophysical simulations as a reference standard, bridging the gap between theoretical understanding and experimental observation through data-driven inference.