Frontiers Ps and Qs: Quantization-Aware Pruning for Efficient Low Latency Neural Network Inference

Machine Learning Systems - 10 Model Optimizations

Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference

Quantized Training with Deep Networks, by Cameron R. Wolfe, Ph.D.

Accuracy of ResNet-50 quantized to 2 and 4 bits, respectively.

2106.08295] A White Paper on Neural Network Quantization

Chips, Free Full-Text

Visualization of the loss surface as a function of quantization ranges

Sensors, Free Full-Text

Network Pruning