4.6 (532) · $ 10.50 · In stock
Frontiers Quantization Framework for Fast Spiking Neural Networks
PDF) End-to-end codesign of Hessian-aware quantized neural networks for FPGAs and ASICs
PDF) Neural Network Quantization for Efficient Inference: A Survey
Accuracy of ResNet-50 quantized to 2 and 4 bits, respectively.
arxiv-sanity
2006.10159] Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors
Quantization vs Pruning vs Distillation: Optimizing NNs for Inference
Frontiers Neuron pruning in temporal domain for energy efficient SNN processor design
PDF] Channel-wise Hessian Aware trace-Weighted Quantization of Neural Networks
Network Pruning