A Gradient-Based Yet Spike-Timing-Dependent Solution to the Feedback Learning Problem in Neural Microcircuits

MCML Authors

Björn Schuller

Prof. Dr.

Core PI

Health Informatics

Abstract

The brain uses discrete spikes for dynamic computation, yet, how neural microcircuits (NMCs) solve temporal credit assignment using local spike timing remains a fundamental open question. Dominant spiking neural network (SNN) approaches circumvent this by approximating backpropagation through surrogate gradients, decoupling learning from biological spike timing. Here, we reformulate temporal credit assignment as a state separation problem: extracting task-required components induced by historical perturbations directly from the current neural state. This enables an online feedback learning framework for NMCs through a gradient tunneling (GT) algorithm and the lead-lag expansion technique that derives credit assignment from local synaptic spike timing, while remaining compatible with ANN-SNN hybrid architectures. Experimentally, GT-trained NMCs excel at long-timescale evidence integration and noise-robust memory retention, and perform comparably to leading SNN online learning methods on real-world benchmarks with far fewer parameters. The proposed framework addresses the two-decade-old NMC feedback learning problem and suggests a computationally plausible explanation for the brain's learning mechanisms.

misc ZLL+26

---

Preprint

Sep. 2026

---

Authors

X. Zhang • J. Liu • R. Lu • J. Liu • Q. Dong • F. Tian • L. Zhu • B. Hu • B. W. Schuller

---

Links

arXiv GitHub

---

Research Area

 B3 | Multimodal Perception