Merge pull request Efficient-ML#6 from ssh9919/pr

Add some papers.

README.md

@@ -104,6 +104,7 @@ Amir Gholami\* , Sehoon Kim\* , Zhen Dong\* , Zhewei Yao\* , Michael W. Mahoney,
 ### 2020
 
 - [[ACL](https://www.aclweb.org/anthology/2020.sustainlp-1.4.pdf)] End to End Binarized Neural Networks for Text Classification. [**`binarization`**] <!--citation 0-->
+- [[AAAI](https://aaai.org/ojs/index.php/AAAI/article/view/6035)] HLHLp: Quantized Neural Networks Traing for Reaching Flat Minima in Loss Sufrface. [__`low-bit`__] 
 - [[AAAI](https://arxiv.org/abs/1909.05840)] [72:fire:] Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT.  [__`low-bit`__] [**`nlp`**]
 - [[AAAI](https://aaai.org/ojs/index.php/AAAI/article/view/6900)] Sparsity-Inducing Binarized Neural Networks. [**`binarization`**] 
 - [[AAAI](https://aaai.org/ojs/index.php/AAAI/article/view/6134)] Towards Accurate Low Bit-Width Quantization with Multiple Phase Adaptations. 
@@ -285,6 +286,7 @@ Amir Gholami\* , Sehoon Kim\* , Zhen Dong\* , Zhewei Yao\* , Michael W. Mahoney,
 - [[CVPR](https://openaccess.thecvf.com/content_cvpr_2017/papers/Cai_Deep_Learning_With_CVPR_2017_paper.pdf)] [251:fire:] Deep Learning with Low Precision by Half-wave Gaussian Quantization. [**`low-bit`**] [[code](https://github.com/zhaoweicai/hwgq)] [118:star:] 
 - [[CVPR](https://openaccess.thecvf.com/content_cvpr_2017/papers/Juefei-Xu_Local_Binary_Convolutional_CVPR_2017_paper.pdf)] [156:fire:] Local Binary Convolutional Neural Networks. [**`binarization`**] [[torch](https://github.com/juefeix/lbcnn.torch)] [94:star:] 
 - [[FPGA](https://arxiv.org/abs/1612.07119)] [463:fire:] FINN: A Framework for Fast, Scalable Binarized Neural Network Inference. [**`hardware`**] [**`binarization`**] 
+- [[ICASSP](https://arxiv.org/abs/1702.08171))] Fixed-point optimization of deep neural networks with adaptive step size retraining. [**`low-bit`**]
 - [[ICCV](https://openaccess.thecvf.com/content_ICCV_2017/papers/Bulat_Binarized_Convolutional_Landmark_ICCV_2017_paper.pdf)] [130:fire:] Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources.  [**`binarization`**] [[homepage](https://www.adrianbulat.com/binary-cnn-landmarks)] [[torch](https://github.com/1adrianb/binary-human-pose-estimation)] [207:star:]
 - [[ICCV](https://openaccess.thecvf.com/content_ICCV_2017/papers/Li_Performance_Guaranteed_Network_ICCV_2017_paper.pdf)] [55:fire:] Performance Guaranteed Network Acceleration via High-Order Residual Quantization.  [**`low-bit`**] 
 - [[ICLR](https://openreview.net/pdf?id=HyQJ-mclg)] [554:fire:] Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights. [**`low-bit`**] [[torch](https://github.com/Mxbonn/INQ-pytorch)] [144:star:] 
@@ -304,6 +306,7 @@ Amir Gholami\* , Sehoon Kim\* , Zhen Dong\* , Zhewei Yao\* , Michael W. Mahoney,
 
 - [[CoRR](http://arxiv.org/abs/1606.06160)] [1k:fire:] DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients. [**`low-bit`**] [[code](https://github.com/tensorpack/tensorpack/tree/master/examples/DoReFa-Net)] [5.8k:star:] 
 - [[ECCV](https://arxiv.org/abs/1603.05279)] [2.7k:fire:] XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks. [**`binarization`**] [[torch](https://github.com/allenai/XNOR-Net)] [787:star:] 
+- [[ICASSP](https://arxiv.org/abs/1512.01322))] Fixed-point Performance Analysis of Recurrent Neural Networks. [**`low-bit`**]
 - [[NeurIPS](https://arxiv.org/pdf/1605.04711.pdf)] [572:fire:] Ternary weight networks.  [**`low-bit`**] [[code](https://github.com/fengfu-chris/caffe-twns)] [61:star:] 
 - [[NeurIPS](https://arxiv.org/pdf/1602.02830))] [1.7k:fire:] Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1. [**`binarization`**] [[torch](https://github.com/itayhubara/BinaryNet)] [239:star:] 
 
@@ -313,6 +316,7 @@ Amir Gholami\* , Sehoon Kim\* , Zhen Dong\* , Zhewei Yao\* , Michael W. Mahoney,
 
 - [[ICML](https://arxiv.org/abs/1601.06071)] [191:fire:] Bitwise Neural Networks. [**`binarization`**] 
 - [[NeurIPS](https://arxiv.org/abs/1511.00363)] [1.8k:fire:] BinaryConnect: Training Deep Neural Networks with binary weights during propagations. [**`binarization`**] [[code](https://github.com/MatthieuCourbariaux/BinaryConnect)] [330:star:] 
+- [[arxiv](https://arxiv.org/abs/1511.06488)] Resiliency of Deep Neural Networks under quantizations. [**`low-bit`**]