A fixed refractory period, implemented as a strided temporal convolution, can replace LIF reset dynamics in a state-space spiking model and still produce sparse, parallel-trainable spikes.
Spike-based neuromorphic model for sound source localization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Revisiting Reset Mechanisms in Spiking Neural Networks for Sequential Modeling: Specialized Discretization for Binary Activated RNN
A fixed refractory period, implemented as a strided temporal convolution, can replace LIF reset dynamics in a state-space spiking model and still produce sparse, parallel-trainable spikes.