Open access
Jul 2026
From Hodgkin-Huxley to Pretrained Neural Inference AI
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.
Yimu Zhang, Dong-Qi Han, Zhen-Ning Lv et al.
· bioRxiv · 0 citations