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.
Toward high-accuracy and low-latency spiking neural net- works with two-stage optimization.IEEE Transactions on Neural Networks and Learning Systems, 2023b
1 Pith paper cite this work, alongside 10 external citations. Polarity classification is still indexing.
1
Pith paper citing it
10
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
fields
cs.NE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 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.