<ul><li>Spiking Neural Networks (SNNs) are energy-efficient neural networks for neuromorphic hardware.</li><li>Weight pruning and quantization are used to improve SNNs' efficiency on hardware with limited resources.</li><li>A new one-shot post-training pruning/quantization framework, Optimal Spiking Brain Compression (OSBC), is proposed.</li><li>OSBC achieves efficient SNN compression by minimizing the loss on spiking neuron membrane potential with a small sample dataset.</li></ul>

Optimal Spiking Brain Compression: Improving One-Shot Post-Training Pruning and Quantization for Spiking Neural Networks

Discover more