1. FINN
2. How to train a compact binary neural network with high accuracy?;tang;Proc AAAI Conf on Arti Intel,2017
3. Model compression via distillation and quantization;polino;Proc Int Conf Learn Repren,2018
4. Automatic differentiation in pytorch;paszke;Proc Adv Neural Inf Process Syst Workshops,2017
5. Weighted-Entropy-Based Quantization for Deep Neural Networks