ReverB-SNN replaces binary spikes with real-valued spikes and real weights with binary weights, keeping SNN inference addition-only while improving accuracy.
Deep residual learning in spiking neural net- works
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
-
ReverB-SNN: Reversing Bit of the Weight and Activation for Spiking Neural Networks
ReverB-SNN replaces binary spikes with real-valued spikes and real weights with binary weights, keeping SNN inference addition-only while improving accuracy.