Multi-timescale Conductance Spiking Networks
Multi-timescale Conductance Spiking Networks
Auto-generated stub. Edit this file to add more details.
A gradient-trainable spiking neural network framework that achieves rich firing dynamics and high sparsity by parameterizing neuronal conductance timescales.
Why It Matters
This framework enables direct backpropagation through time in spiking neural networks without surrogate gradients by shaping neuronal I-V curves through multi-timescale conductances.
Evidence
we introduce multi-timescale conductance spiking networks, a gradient-trainable framework in which neural dynamics emerge from shaping the current-voltage (I-V) curve by tuning fast, slow and ultra-slow conductances.
Related Papers
Metadata & Links
- created_at
- 2026-05-15T06:16:28Z