A Gradient-based yet Spike-Timing-Dependent Solution to the Feedback Learning Problem in Neural Microcircuits
This work reformulates temporal credit assignment as a state separation problem: extracting task-required components induced by historical perturbations directly from the current neural state, which enables an online feedback learning framework for NMCs through a gradient tunneling algorithm and the lead-lag expansion...
Xiang-Nan Zhang, Jing-Xin Liu, Ran-Qi Lu et al.
· 0 citations