1. Value-aware quantization for training and inference of neural networks;park;ECCV,2018
2. PROFIT: A Novel Training Method for sub-4-bit MobileNet Models
3. Bi-real net: Enhancing the performance of 1-bit cnns with improved representational capability and advanced training algorithm;liu;ECCV,2018
4. Neural networks with few multiplications;lin;ICLRE,2016
5. Overcoming challenges in fixed point training of deep convolutional networks;lin;ICML Workshop,2016