[1] O Russakovsky, J Deng, H Su et al. Imagenet large scale visual recognition challenge. Int J Comput Vision, 115, 211(2015).
[2] A Krizhevsky, I Sutskever, G E Hinton. Imagenet classification with deep convolutional neural networks. Adv Neural Inform Process Syst, 1097(2012).
[3] K He, X Zhang, S Ren et al. Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770(2016).
[4] S Han, J Pool, J Tran et al. Learning both weights and connections for efficient neural network. Adv Neural Inform Process Syst, 1135(2015).
[5]
[6]
[7] H Li, S De, Z Xu et al. Training quantized nets: A deeper understanding. Adv Neural Inform Process Syst, 5811(2017).
[8]
[9]
[10]
[11]
[12]
[13]
[14] R Banner, I Hubara, E Hoffer et al. Scalable methods for 8-bit training of neural networks. Adv Neural Inform Process Syst, 5145(2018).
[15] I Hubara, M Courbariaux, D Soudry et al. Quantized neural networks: Training neural networks with low precision weights and activations. J Mach Learning Res, 18, 6869(2017).
[16] S Gupta, A Agrawal, K Gopalakrishnan et al. Deep learning with limited numerical precision. International Conference on Machine Learning, 1737(2015).
[17] Sa C De, M Feldman, C Ré et al. Understanding and optimizing asynchronous low-precision stochastic gradient descent. ACM SIGARCH Computer Architecture News, 45, 461(2017).
[18]
[19]
[20]
[21]
[22]
[23]
[24] M Courbariaux, Y Bengio, J P David. Binaryconnect: Training deep neural networks with binary weights during propagations. Adv Neural Inform Process Syst, 3123(2015).
[25] I Hubara, M Courbariaux, D Soudry et al. Binarized neural networks. Adv Neural Inform Process Syst, 4107(2016).
[26] M Rastegari, V Ordonez, J Redmon et al. Xnor-net: Imagenet classification using binary convolutional neural networks. European Conference on Computer Vision, 525(2016).
[27]
[28]