A quantized and pruned spiking neural network with weight rescaling and singular-value-based pruning reaches comparable accuracy at roughly a tenth of the model size.
Binary event-driven spiking transformer.arXiv preprint arXiv:2501.05904,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
QP-SNN: Quantized and Pruned Spiking Neural Networks
A quantized and pruned spiking neural network with weight rescaling and singular-value-based pruning reaches comparable accuracy at roughly a tenth of the model size.