└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Efficient-Deep-Learning 2 | Related Paper of Efficient Deep Neural Networks 3 | 4 | ## Reviews, Tutorials, Blog 5 | 1. [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://arxiv.org/abs/1703.09039) 6 | 2. [High-Performance Hardware for Machine Learning](https://media.nips.cc/Conferences/2015/tutorialslides/Dally-NIPS-Tutorial-2015.pdf) 7 | 3. [series of deep learning on iphone blogs](http://machinethink.net/blog/) 8 | ## Sparse, Quantization and Compression 9 | 10 | ### Sparse 11 | 1. [Learning both Weights and Connections for Efficient Neural Networks](https://arxiv.org/abs/1506.02626) [NIPS 2015] 12 | 2. [Dynamic Network Surgery for Efficient DNNs](https://arxiv.org/abs/1608.04493) [NIPS2016] [Code](https://github.com/yiwenguo/Dynamic-Network-Surgery) 13 | 3. [Learning Structured Sparsity in Deep Neural Networks](https://arxiv.org/abs/1608.03665) [NIPS 2016] [Code](https://github.com/wenwei202/caffe/tree/scnn) 14 | 4. [Sparse Convolutional Neural Networks](http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Liu_Sparse_Convolutional_Neural_2015_CVPR_paper.pdf) [CVPR 2015] 15 | 5. [Pruning Filters for Efficient ConvNets](https://openreview.net/pdf?id=rJqFGTslg) [ICLR 2017] 16 | 17 | 18 | ### Quantization 19 | 1. [Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights](https://arxiv.org/abs/1702.03044) [ICLR 2017] 20 | 2. [https://arxiv.org/pdf/1706.02393.pdf] 21 | 2. [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://arxiv.org/pdf/1510.00149v5.pdf) [ICLR 2016] 22 | 3. [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://arxiv.org/abs/1603.05279) [ECCV 2016] [Code](https://github.com/allenai/XNOR-Net) 23 | 4. [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://www.arxiv.org/abs/1609.07061) 24 | 5. [Trained Tenary Quantization](https://arxiv.org/abs/1612.01064) [ICLR2017] [Code](https://github.com/czhu95/ternarynet) 25 | 6. [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://arxiv.org/abs/1606.06160) [Code](https://github.com/ppwwyyxx/tensorpack/tree/master/examples/DoReFa-Net) 26 | 7. [Binaryconnect: Training deep neural networks with binary weights during propagations](https://arxiv.org/pdf/1511.00363.pdf) [NIPS 2015] 27 | 8. [Binarize neural networks: Training deep neural networks with weights and activations constrained to +1 or -1](https://arxiv.org/abs/1602.02505) [NIPS 2016] 28 | 9. [Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://arxiv.org/abs/1609.08144) 29 | 10. [8-Bit Approximations For Parallelism In Deep Learning](https://arxiv.org/abs/1511.04561) [ICLR 2016] 30 | 11. [Quantized Convolutional Neural Networks for Mobile Devices] 31 | 32 | ## Light Network Structure 33 | 1. [SqueezeNet: AlexNet-Level Accuracy with 50x Fewer Parameters and < 0.5MB Model Size](https://arxiv.org/pdf/1602.07360v3.pdf) 34 | 2. [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://arxiv.org/abs/1704.04861v1) [Code](https://github.com/pby5/MobileNet_Caffe) 35 | 3. [PVANet: Lightweight Deep Neural Networks for Real-time Object Detection](https://github.com/sanghoon/pva-faster-rcnn) [Code](https://arxiv.org/abs/1611.08588) 36 | 4. 37 | 38 | ## Distillation 39 | 1. [Distilling the Knowledge in a Neural Network](https://arxiv.org/abs/1503.02531) [NIPS 2014] 40 | ## Speed Up 41 | 1. [Fast Training of Convolutional Networks through FFTs](https://arxiv.org/abs/1312.5851) [ICLR 2013] [Code](https://github.com/Maratyszcza/NNPACK) 42 | 2. [Fast algorithms for convolutional neural networks]() [CVPR 2016] 43 | 44 | 45 | ## Hardware Optimation 46 | 1. 47 | 2. 48 | ## Related company and product 49 | 1.[Movidius](https://www.movidius.com/solutions) 50 | 51 | 2.[DeePhi Tech](http://www.deephi.com/) 52 | 53 | 3.[Google TPU]() 54 | 55 | 56 | 57 | 58 | 4.[Nvidia Tesla V100](https://devblogs.nvidia.com/parallelforall/inside-volta/) 59 | 60 | --------------------------------------------------------------------------------