A spiking neural network with offline-learned, frozen convolution kernels classifies five street-object classes at 91.6% accuracy, compared with 92.3% for a similarly shaped CNN.
Training deep spiking convolutional neural networks with STDP -based unsupervised pre - training followed by supervised fine -tuning,
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
-
Convolutional Spiking Neural Network for Image Classification
A spiking neural network with offline-learned, frozen convolution kernels classifies five street-object classes at 91.6% accuracy, compared with 92.3% for a similarly shaped CNN.