Fixed-point iteration with a sigmoid surrogate lets all T timesteps of a LIF neuron be processed in K=3 parallel iterations, matching BPTT accuracy with large speedups.
9 Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity El Ghaoui, L., Gu, F., Travacca, B., Askari, A., and Tsai, A
1 Pith paper cite this work, alongside 26 external citations. Polarity classification is still indexing.
1
Pith paper citing it
26
external citations · OpenAlex
fields
cs.NE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity
Fixed-point iteration with a sigmoid surrogate lets all T timesteps of a LIF neuron be processed in K=3 parallel iterations, matching BPTT accuracy with large speedups.