如果你有非常大的决心从事深度学习,又不想在这一行打酱油,那么研读大牛论文将是不可避免的一步。而作为新人,你的第一个问题或许是:“论文那么多,从哪一篇读起?”

本文将试图解决这个问题——文章标题本来是:“从入门到绝望,无止境的深度学习论文”。请诸位备好道具,开启头悬梁锥刺股的学霸姿势。

开个玩笑。

但对非科班出身的开发者而言,读论文的确可以成为一件很痛苦的事。但好消息来了——为避免初学者陷入迷途苦海,昵称为 songrotek 的学霸在 GitHub 发布了他整理的深度学习路线图,分门别类梳理了新入门者最需要学习的 DL 论文,又按重要程度给每篇论文打上星星。

截至目前,这份 DL 论文路线图已在 GitHub 收获了近万颗星星好评,人气极高。雷锋网感到非常有必要对大家进行介绍。

闲话少说,该路线图根据以下四项原则而组织:

  • 从大纲到细节

  • 从经典到前沿

  • 从一般到具体领域

  • 关注最新研究突破

作者注:有许多论文很新但非常值得一读。

1 深度学习历史和基础

1.0 书籍

█[0] Bengio, Yoshua, Ian J. Goodfellow, and Aaron Courville. "Deep learning." An MIT Press book. (2015). [pdf] (Ian Goodfellow 等大牛所著的教科书,乃深度学习圣经。你可以同时研习这本书以及以下论文) ★★★★★

地址:pLearningBook/raw/master/DeepLearningBook.pdf

1.1 调查

█[1] LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep learning." Nature 521.7553 (2015): 436-444. [pdf] (三巨头做的调查) ★★★★★

地址:absps/NatureDeepReview.pdf

1.2 深度置信网络 (DBN,深度学习前夜的里程碑)

█[2] Hinton, Geoffrey E., Simon Osindero, and Yee-Whye Teh. "A fast learning algorithm for deep belief nets." Neural computation 18.7 (2006): 1527-1554. [pdf] (深度学习前夜) ★★★

地址:absps/ncfast.pdf

█[3] Hinton, Geoffrey E., and Ruslan R. Salakhutdinov. "Reducing the dimensionality of data with neural networks." Science 313.5786 (2006): 504-507. [pdf] (里程碑,展示了深度学习的前景) ★★★

地址:science.pdf

1.3 ImageNet 的进化(深度学习从此萌发)

█[4] Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012. [pdf] (AlexNet, 深度学习突破) ★★★★★

地址:24-imagenet-classification-with-deep-convolutional-neural-networks.pdf

█[5] Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014). [pdf] (VGGNet,神经网络变得很深层) ★★★

地址:.pdf

█[6] Szegedy, Christian, et al. "Going deeper with convolutions." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015. [pdf] (GoogLeNet) ★★★

地址:ccess/content_cvpr_2015/papers/Szegedy_Going_Deeper_With_2015_CVPR_paper.pdf

█[7] He, Kaiming, et al. "Deep residual learning for image recognition." arXiv preprint arXiv:1512.03385 (2015). [pdf](ResNet,特别深的神经网络, CVPR 最佳论文) ★★★★★

地址:5.pdf

1.4 语音识别的进化

█[8] Hinton, Geoffrey, et al. "Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups." IEEE Signal Processing Magazine 29.6 (2012): 82-97. [pdf] (语音识别的突破) ★★★★

地址:ers/maas_paper.pdf

█[9] Graves, Alex, Abdel-rahman Mohamed, and Geoffrey Hinton. "Speech recognition with deep recurrent neural networks." 2013 IEEE international conference on acoustics, speech and signal processing. IEEE, 2013. [pdf] (RNN) ★★★

地址:.pdf

█[10] Graves, Alex, and Navdeep Jaitly. "Towards End-To-End Speech Recognition with Recurrent Neural Networks." ICML. Vol. 14. 2014. [pdf] ★★★

地址:pers/v32/graves14.pdf

█[11] Sak, Haşim, et al. "Fast and accurate recurrent neural network acoustic models for speech recognition." arXiv preprint arXiv:1507.06947 (2015). [pdf] (谷歌语音识别系统) ★★★

地址:7

█[12] Amodei, Dario, et al. "Deep speech 2: End-to-end speech recognition in english and mandarin." arXiv preprint arXiv:1512.02595 (2015). [pdf] (百度语音识别系统) ★★★★

地址:5.pdf

█[13] W. Xiong, J. Droppo, X. Huang, F. Seide, M. Seltzer, A. Stolcke, D. Yu, G. Zweig "Achieving Human Parity in Conversational Speech Recognition." arXiv preprint arXiv:1610.05256 (2016). [pdf] (最前沿的语音识别, 微软) ★★★★

地址:6v1

研读以上论文之后,你将对深度学习历史、模型的基本架构(包括 CNN, RNN, LSTM)有一个基础的了解,并理解深度学习如何应用于图像和语音识别问题。接下来的论文,将带你深入探索深度学习方法、在不同领域的应用和前沿尖端技术。我建议,你可以根据兴趣和工作/研究方向进行选择性的阅读。

2 深度学习方法

2.1 模型

█[14] Hinton, Geoffrey E., et al. "Improving neural networks by preventing co-adaptation of feature detectors." arXiv preprint arXiv:1207.0580 (2012). [pdf] (Dropout) ★★★

地址:.pdf

█[15] Srivastava, Nitish, et al. "Dropout: a simple way to prevent neural networks from overfitting." Journal of Machine Learning Research 15.1 (2014): 1929-1958. [pdf] ★★★

地址:5/srivastava14a.old/source/srivastava14a.pdf

█[16] Ioffe, Sergey, and Christian Szegedy. "Batch normalization: Accelerating deep network training by reducing internal covariate shift." arXiv preprint arXiv:1502.03167 (2015). [pdf] (2015 年的杰出研究) ★★★★

地址:7

█[17] Ba, Jimmy Lei, Jamie Ryan Kiros, and Geoffrey E. Hinton. "Layer normalization." arXiv preprint arXiv:1607.06450 (2016). [pdf] (Batch Normalization 的更新) ★★★★

地址:0.pdf?utm_source=sciontist.com&utm_medium=refer&utm_campaign=promote

█[18] Courbariaux, Matthieu, et al. "Binarized Neural Networks: Training Neural Networks with Weights and Activations Constrained to+ 1 or−1." [pdf] (新模型,快) ★★★

地址:/f832/b16cb367802609d91d400085eb87d630212a.pdf

█[19] Jaderberg, Max, et al. "Decoupled neural interfaces using synthetic gradients." arXiv preprint arXiv:1608.05343 (2016). [pdf] (训练方法的创新,研究相当不错) ★★★★★

地址:3

█[20] Chen, Tianqi, Ian Goodfellow, and Jonathon Shlens. "Net2net: Accelerating learning via knowledge transfer." arXiv preprint arXiv:1511.05641 (2015). [pdf] (改进此前的训练网络,来缩短训练周期) ★★★

地址:Accelerating Learning via Knowledge Transfer

█[21] Wei, Tao, et al. "Network Morphism." arXiv preprint arXiv:1603.01670 (2016). [pdf] (改进此前的训练网络,来缩短训练周期) ★★★

地址:[1603.01670] Network Morphism

2.2 优化 Optimization

█[22] Sutskever, Ilya, et al. "On the importance of initialization and momentum in deep learning." ICML (3) 28 (2013): 1139-1147. [pdf] (Momentum optimizer) ★★

地址:pers/v28/sutskever13.pdf

█[23] Kingma, Diederik, and Jimmy Ba. "Adam: A method for stochastic optimization." arXiv preprint arXiv:1412.6980 (2014). [pdf] (Maybe used most often currently) ★★★

地址:arxiv.org/pdf/1412.6980

█[24] Andrychowicz, Marcin, et al. "Learning to learn by gradient descent by gradient descent." arXiv preprint arXiv:1606.04474 (2016). [pdf] (Neural Optimizer,Amazing Work) ★★★★★

地址:4

█[25] Han, Song, Huizi Mao, and William J. Dally. "Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding." CoRR, abs/1510.00149 2 (2015). [pdf] (ICLR best paper, new direction to make NN running fast,DeePhi Tech Startup) ★★★★★

地址:/5b6c/9dda1d88095fa4aac1507348e498a1f2e863.pdf

█[26] Iandola, Forrest N., et al. "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 1MB model size." arXiv preprint arXiv:1602.07360 (2016). [pdf] (Also a new direction to optimize NN,DeePhi Tech Startup) ★★★★

地址:0

2.3 无监督学习/深度生成模型

█[27] Le, Quoc V. "Building high-level features using large scale unsupervised learning." 2013 IEEE international conference on acoustics, speech and signal processing. IEEE, 2013. [pdf] (里程碑, 吴恩达, 谷歌大脑, Cat) ★★★★

地址:.pdf&embed

█[28] Kingma, Diederik P., and Max Welling. "Auto-encoding variational bayes." arXiv preprint arXiv:1312.6114 (2013). [pdf](VAE) ★★★★

地址:arxiv.org/pdf/1312.6114

█[29] Goodfellow, Ian, et al. "Generative adversarial nets." Advances in Neural Information Processing Systems. 2014. [pdf](GAN,很酷的想法) ★★★★★

地址:23-generative-adversarial-nets.pdf

█[30] Radford, Alec, Luke Metz, and Soumith Chintala. "Unsupervised representation learning with deep convolutional generative adversarial networks." arXiv preprint arXiv:1511.06434 (2015). [pdf] (DCGAN) ★★★★

地址:4

█[31] Gregor, Karol, et al. "DRAW: A recurrent neural network for image generation." arXiv preprint arXiv:1502.04623 (2015). [pdf] (VAE with attention, 很出色的研究) ★★★★★

地址:pers/v37/gregor15.pdf

█[32] Oord, Aaron van den, Nal Kalchbrenner, and Koray Kavukcuoglu. "Pixel recurrent neural networks." arXiv preprint arXiv:1601.06759 (2016). [pdf] (PixelRNN) ★★★★

地址:9

█[33] Oord, Aaron van den, et al. "Conditional image generation with PixelCNN decoders." arXiv preprint arXiv:1606.05328 (2016). [pdf] (PixelCNN) ★★★★

地址:8

2.4 递归神经网络(RNN) / Sequence-to-Sequence Model

█[34] Graves, Alex. "Generating sequences with recurrent neural networks." arXiv preprint arXiv:1308.0850 (2013). [pdf] (LSTM, 效果很好,展示了 RNN 的性能) ★★★★

地址:arxiv.org/pdf/1308.0850

█[35] Cho, Kyunghyun, et al. "Learning phrase representations using RNN encoder-decoder for statistical machine translation." arXiv preprint arXiv:1406.1078 (2014). [pdf] (第一篇 Sequence-to-Sequence 的论文) ★★★★

地址:arxiv.org/pdf/1406.1078

█[36] Sutskever, Ilya, Oriol Vinyals, and Quoc V. Le. "Sequence to sequence learning with neural networks." Advances in neural information processing systems. 2014. [pdf] (杰出研究) ★★★★★

地址:46-information-based-learning-by-agents-in-unbounded-state-spaces.pdf

█[37] Bahdanau, Dzmitry, KyungHyun Cho, and Yoshua Bengio. "Neural Machine Translation by Jointly Learning to Align and Translate." arXiv preprint arXiv:1409.0473 (2014). [pdf] ★★★★

地址:v7.pdf

█[38] Vinyals, Oriol, and Quoc Le. "A neural conversational model." arXiv preprint arXiv:1506.05869 (2015). [pdf] (Seq-to-Seq 聊天机器人) ★★★

地址:9.pdf%20(http://arxiv.org/pdf/1506.05869.pdf)

2.5 神经网络图灵机

█[39] Graves, Alex, Greg Wayne, and Ivo Danihelka. "Neural turing machines." arXiv preprint arXiv:1410.5401 (2014). [pdf] (未来计算机的基础原型机) ★★★★★

地址:.pdf

█[40] Zaremba, Wojciech, and Ilya Sutskever. "Reinforcement learning neural Turing machines." arXiv preprint arXiv:1505.00521 362 (2015). [pdf] ★★★

地址:/f10e/071292d593fef939e6ef4a59baf0bb3a6c2b.pdf

█[41] Weston, Jason, Sumit Chopra, and Antoine Bordes. "Memory networks." arXiv preprint arXiv:1410.3916 (2014). [pdf] ★★★

地址:arxiv.org/pdf/1410.3916

█[42] Sukhbaatar, Sainbayar, Jason Weston, and Rob Fergus. "End-to-end memory networks." Advances in neural information processing systems. 2015. [pdf] ★★★★

地址:46-end-to-end-memory-networks.pdf

█[43] Vinyals, Oriol, Meire Fortunato, and Navdeep Jaitly. "Pointer networks." Advances in Neural Information Processing Systems. 2015. [pdf] ★★★★

地址:66-pointer-networks.pdf

█[44] Graves, Alex, et al. "Hybrid computing using a neural network with dynamic external memory." Nature (2016). [pdf] (里程碑,把以上论文的想法整合了起来) ★★★★★

地址:grx3dq/2016-graves.pdf

2.6 深度强化学习

█[45] Mnih, Volodymyr, et al. "Playing atari with deep reinforcement learning." arXiv preprint arXiv:1312.5602 (2013). [pdf]) (第一个以深度强化学习为题的论文) ★★★★

地址:.pdf

█[46] Mnih, Volodymyr, et al. "Human-level control through deep reinforcement learning." Nature 518.7540 (2015): 529-533. [pdf] (里程碑) ★★★★★

地址:deepmind-data/assets/papers/DeepMindNature14236Paper.pdf

█[47] Wang, Ziyu, Nando de Freitas, and Marc Lanctot. "Dueling network architectures for deep reinforcement learning." arXiv preprint arXiv:1511.06581 (2015). [pdf] (ICLR 最佳论文,很棒的想法) ★★★★

地址:1

█[48] Mnih, Volodymyr, et al. "Asynchronous methods for deep reinforcement learning." arXiv preprint arXiv:1602.01783 (2016). [pdf] (前沿方法) ★★★★★

地址:3

█[49] Lillicrap, Timothy P., et al. "Continuous control with deep reinforcement learning." arXiv preprint arXiv:1509.02971 (2015). [pdf] (DDPG) ★★★★

地址:1

█[50] Gu, Shixiang, et al. "Continuous Deep Q-Learning with Model-based Acceleration." arXiv preprint arXiv:1603.00748 (2016). [pdf] (NAF) ★★★★

地址:8

█[51] Schulman, John, et al. "Trust region policy optimization." CoRR, abs/1502.05477 (2015). [pdf] (TRPO) ★★★★

地址:pers/v37/schulman15.pdf

█[52] Silver, David, et al. "Mastering the game of Go with deep neural networks and tree search." Nature 529.7587 (2016): 484-489. [pdf] (AlphaGo) ★★★★★

地址:k/cs448/goNature.pdf

2.7 深度迁移学习 /终生学习 / 强化学习

█[53] Bengio, Yoshua. "Deep Learning of Representations for Unsupervised and Transfer Learning." ICML Unsupervised and Transfer Learning 27 (2012): 17-36. [pdf] (这是一个教程) ★★★

地址:pers/v27/bengio12a/bengio12a.pdf

█[54] Silver, Daniel L., Qiang Yang, and Lianghao Li. "Lifelong Machine Learning Systems: Beyond Learning Algorithms." AAAI Spring Symposium: Lifelong Machine Learning. 2013. [pdf] (对终生学习的简单讨论) ★★★

地址:iewdoc/download?doi=10.1.1.696.7800&rep=rep1&type=pdf

█[55] Hinton, Geoffrey, Oriol Vinyals, and Jeff Dean. "Distilling the knowledge in a neural network." arXiv preprint arXiv:1503.02531 (2015). [pdf] (大神们的研究) ★★★★

地址:1

█[56] Rusu, Andrei A., et al. "Policy distillation." arXiv preprint arXiv:1511.06295 (2015). [pdf] (RL 领域) ★★★

地址:5

█[57] Parisotto, Emilio, Jimmy Lei Ba, and Ruslan Salakhu★★★tdinov. "Actor-mimic: Deep multitask and transfer reinforcement learning." arXiv preprint arXiv:1511.06342 (2015). [pdf] (RL 领域) ★★★

地址:2

█[58] Rusu, Andrei A., et al. "Progressive neural networks." arXiv preprint arXiv:1606.04671 (2016). [pdf] (杰出研究, 很新奇的想法) ★★★★★

地址:1

2.8 One Shot 深度学习

█[59] Lake, Brenden M., Ruslan Salakhutdinov, and Joshua B. Tenenbaum. "Human-level concept learning through probabilistic program induction." Science 350.6266 (2015): 1332-1338. [pdf] (不含深度学习但值得一读) ★★★★★

地址:b/wp-content/uploads/2016/02/lake2015.pdf

█[60] Koch, Gregory, Richard Zemel, and Ruslan Salakhutdinov. "Siamese Neural Networks for One-shot Image Recognition."(2015) [pdf] ★★★

地址:iles/msc-thesis.pdf

█[61] Santoro, Adam, et al. "One-shot Learning with Memory-Augmented Neural Networks." arXiv preprint arXiv:1605.06065 (2016). [pdf] (one shot 学习的基础一步) ★★★★

地址:5

█[62] Vinyals, Oriol, et al. "Matching Networks for One Shot Learning." arXiv preprint arXiv:1606.04080 (2016). [pdf] ★★★

地址:0

█[63] Hariharan, Bharath, and Ross Girshick. "Low-shot visual object recognition." arXiv preprint arXiv:1606.02819 (2016). [pdf] (通向更大规模数据的一步) ★★★★

地址:9

3 应用

3.1 自然语言处理 (NLP)

█[1] Antoine Bordes, et al. "Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing." AISTATS(2012) [pdf] ★★★★

地址:kuwiki/lib/exe/fetch.php?id=en%3Apubli&cache=cache&media=en:bordes12aistats.pdf

█[2] Mikolov, et al. "Distributed representations of words and phrases and their compositionality." ANIPS(2013): 3111-3119 [pdf] (word2vec) ★★★

地址:21-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf

█[3] Sutskever, et al. "“Sequence to sequence learning with neural networks." ANIPS(2014) [pdf] ★★★

地址:46-sequence-to-sequence-learning-with-neural-networks.pdf

█[4] Ankit Kumar, et al. "“Ask Me Anything: Dynamic Memory Networks for Natural Language Processing." arXiv preprint arXiv:1506.07285(2015) [pdf] ★★★★

地址:5

█[5] Yoon Kim, et al. "Character-Aware Neural Language Models." NIPS(2015) arXiv preprint arXiv:1508.06615(2015) [pdf] ★★★

地址:[1508.06615] Character-Aware Neural Language Models

█[6] Jason Weston, et al. "Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks." arXiv preprint arXiv:1502.05698(2015) [pdf] (bAbI tasks) ★★★

地址:A Set of Prerequisite Toy Tasks

█[7] Karl Moritz Hermann, et al. "Teaching Machines to Read and Comprehend." arXiv preprint arXiv:1506.03340(2015) [pdf](CNN/每日邮报完形填空风格的问题) ★★

地址:[1506.03340] Teaching Machines to Read and Comprehend

█[8] Alexis Conneau, et al. "Very Deep Convolutional Networks for Natural Language Processing." arXiv preprint arXiv:1606.01781(2016) [pdf] (文本分类的前沿技术) ★★★

地址:[1606.01781] Very Deep Convolutional Networks for Text Classification

█[9] Armand Joulin, et al. "Bag of Tricks for Efficient Text Classification." arXiv preprint arXiv:1607.01759(2016) [pdf] (比前沿技术稍落后, 但快很多) ★★★

地址:[1607.01759] Bag of Tricks for Efficient Text Classification

3.2 物体检测

█[1] Szegedy, Christian, Alexander Toshev, and Dumitru Erhan. "Deep neural networks for object detection." Advances in Neural Information Processing Systems. 2013. [pdf] ★★★

地址:07-deep-neural-networks-for-object-detection.pdf

█[2] Girshick, Ross, et al. "Rich feature hierarchies for accurate object detection and semantic segmentation." Proceedings of the IEEE conference on computer vision and pattern recognition. 2014. [pdf] (RCNN) ★★★★★

地址:ccess/content_cvpr_2014/papers/Girshick_Rich_Feature_Hierarchies_2014_CVPR_paper.pdf

█[3] He, Kaiming, et al. "Spatial pyramid pooling in deep convolutional networks for visual recognition." European Conference on Computer Vision. Springer International Publishing, 2014. [pdf] (SPPNet) ★★★★

地址:arxiv.org/pdf/1406.4729

█[4] Girshick, Ross. "Fast r-cnn." Proceedings of the IEEE International Conference on Computer Vision. 2015. [pdf] ★★★★

地址:/8f67/64a59f0d17081f2a2a9d06f4ed1cdea1a0ad.pdf

█[5] Ren, Shaoqing, et al. "Faster R-CNN: Towards real-time object detection with region proposal networks." Advances in neural information processing systems. 2015. [pdf] ★★★★

地址:38-analysis-of-variational-bayesian-latent-dirichlet-allocation-weaker-sparsity-than-map.pdf

█[6] Redmon, Joseph, et al. "You only look once: Unified, real-time object detection." arXiv preprint arXiv:1506.02640 (2015). [pdf] (YOLO,杰出研究,非常具有使用价值) ★★★★★

地址:/~ali/papers/YOLO.pdf

█[7] Liu, Wei, et al. "SSD: Single Shot MultiBox Detector." arXiv preprint arXiv:1512.02325 (2015). [pdf] ★★★

地址:5

█[8] Dai, Jifeng, et al. "R-FCN: Object Detection via Region-based Fully Convolutional Networks." arXiv preprint arXiv:1605.06409 (2016). [pdf] ★★★★

地址:Object Detection via Region-based Fully Convolutional Networks

3.3 视觉追踪

█[1] Wang, Naiyan, and Dit-Yan Yeung. "Learning a deep compact image representation for visual tracking." Advances in neural information processing systems. 2013. [pdf] (第一篇使用深度学习做视觉追踪的论文,DLT Tracker) ★★★

地址:92-learning-a-deep-compact-image-representation-for-visual-tracking.pdf

█[2] Wang, Naiyan, et al. "Transferring rich feature hierarchies for robust visual tracking." arXiv preprint arXiv:1501.04587 (2015). [pdf] (SO-DLT) ★★★★

地址:7

█[3] Wang, Lijun, et al. "Visual tracking with fully convolutional networks." Proceedings of the IEEE International Conference on Computer Vision. 2015. [pdf] (FCNT) ★★★★

地址:ccess/content_iccv_2015/papers/Wang_Visual_Tracking_With_ICCV_2015_paper.pdf

█[4] Held, David, Sebastian Thrun, and Silvio Savarese. "Learning to Track at 100 FPS with Deep Regression Networks." arXiv preprint arXiv:1604.01802 (2016). [pdf] (GOTURN,在深度学习方法里算是非常快的,但仍比非深度学习方法慢很多) ★★★★

地址:2

█[5] Bertinetto, Luca, et al. "Fully-Convolutional Siamese Networks for Object Tracking." arXiv preprint arXiv:1606.09549 (2016). [pdf] (SiameseFC,实时物体追踪领域的最新前沿技术) ★★★★

地址:9

█[6] Martin Danelljan, Andreas Robinson, Fahad Khan, Michael Felsberg. "Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking." ECCV (2016) [pdf] (C-COT) ★★★★

地址:/objrec/visualtracking/conttrack/C-COT_ECCV16.pdf

█[7] Nam, Hyeonseob, Mooyeol Baek, and Bohyung Han. "Modeling and Propagating CNNs in a Tree Structure for Visual Tracking." arXiv preprint arXiv:1608.07242 (2016). [pdf] (VOT2016 获奖论文,TCNN) ★★★★

地址:2

3.4 图像标注

█[1] Farhadi,Ali,etal. "Every picture tells a story: Generating sentences from images". In Computer VisionECCV 2010. Springer Berlin Heidelberg:15-29, 2010. [pdf] ★★★

地址:pers/sentence.pdf

█[2] Kulkarni, Girish, et al. "Baby talk: Understanding and generating image descriptions". In Proceedings of the 24th CVPR, 2011. [pdf] ★★★★

地址:eneration_cvpr11.pdf

█[3] Vinyals, Oriol, et al. "Show and tell: A neural image caption generator". In arXiv preprint arXiv:1411.4555, 2014. [pdf] ★★★

地址:.pdf

█[4] Donahue, Jeff, et al. "Long-term recurrent convolutional networks for visual recognition and description". In arXiv preprint arXiv:1411.4389 ,2014. [pdf]

地址:.pdf

█[5] Karpathy, Andrej, and Li Fei-Fei. "Deep visual-semantic alignments for generating image descriptions". In arXiv preprint arXiv:1412.2306, 2014. [pdf] ★★★★★

地址:karpathy/cvpr2015.pdf

█[6] Karpathy, Andrej, Armand Joulin, and Fei Fei F. Li. "Deep fragment embeddings for bidirectional image sentence mapping". In Advances in neural information processing systems, 2014. [pdf] ★★★★

地址:v1.pdf

█[7] Fang, Hao, et al. "From captions to visual concepts and back". In arXiv preprint arXiv:1411.4952, 2014. [pdf] ★★★★★

地址:v3.pdf

█[8] Chen, Xinlei, and C. Lawrence Zitnick. "Learning a recurrent visual representation for image caption generation". In arXiv preprint arXiv:1411.5654, 2014. [pdf] ★★★★

地址:v1.pdf

█[9] Mao, Junhua, et al. "Deep captioning with multimodal recurrent neural networks (m-rnn)". In arXiv preprint arXiv:1412.6632, 2014. [pdf] ★★★

地址:v5.pdf

█[10] Xu, Kelvin, et al. "Show, attend and tell: Neural image caption generation with visual attention". In arXiv preprint arXiv:1502.03044, 2015. [pdf] ★★★★★

地址:4v3.pdf

3.5 机器翻译

部分里程碑研究被列入 RNN / Seq-to-Seq 版块。

█[1] Luong, Minh-Thang, et al. "Addressing the rare word problem in neural machine translation." arXiv preprint arXiv:1410.8206 (2014). [pdf] ★★★★

地址:arxiv.org/pdf/1410.8206

█[2] Sennrich, et al. "Neural Machine Translation of Rare Words with Subword Units". In arXiv preprint arXiv:1508.07909, 2015. [pdf] ★★★

地址:9.pdf

█[3] Luong, Minh-Thang, Hieu Pham, and Christopher D. Manning. "Effective approaches to attention-based neural machine translation." arXiv preprint arXiv:1508.04025 (2015). [pdf] ★★★★

地址:5

[4] Chung, et al. "A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation". In arXiv preprint arXiv:1603.06147, 2016. [pdf] ★★

地址:7.pdf

█[5] Lee, et al. "Fully Character-Level Neural Machine Translation without Explicit Segmentation". In arXiv preprint arXiv:1610.03017, 2016. [pdf] ★★★★★

地址:7.pdf

█[6] Wu, Schuster, Chen, Le, et al. "Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation". In arXiv preprint arXiv:1609.08144v2, 2016. [pdf] (Milestone) ★★★★

地址:4v2.pdf

3.6 机器人

█[1] Koutník, Jan, et al. "Evolving large-scale neural networks for vision-based reinforcement learning." Proceedings of the 15th annual conference on Genetic and evolutionary computation. ACM, 2013. [pdf] ★★★

地址:0/1/koutnik2013gecco.pdf

█[2] Levine, Sergey, et al. "End-to-end training of deep visuomotor policies." Journal of Machine Learning Research 17.39 (2016): 1-40. [pdf] ★★★★★

地址:7/15-522/15-522.pdf

█[3] Pinto, Lerrel, and Abhinav Gupta. "Supersizing self-supervision: Learning to grasp from 50k tries and 700 robot hours." arXiv preprint arXiv:1509.06825 (2015). [pdf] ★★★

地址:5

█[4] Levine, Sergey, et al. "Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection." arXiv preprint arXiv:1603.02199 (2016). [pdf] ★★★★

地址:9

█[5] Zhu, Yuke, et al. "Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning." arXiv preprint arXiv:1609.05143 (2016). [pdf] ★★★★

地址:3

█[6] Yahya, Ali, et al. "Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search." arXiv preprint arXiv:1610.00673 (2016). [pdf] ★★★★

地址:3

█[7] Gu, Shixiang, et al. "Deep Reinforcement Learning for Robotic Manipulation." arXiv preprint arXiv:1610.00633 (2016). [pdf] ★★★★

地址:3

█[8] A Rusu, M Vecerik, Thomas Rothörl, N Heess, R Pascanu, R Hadsell."Sim-to-Real Robot Learning from Pixels with Progressive Nets." arXiv preprint arXiv:1610.04286 (2016). [pdf] ★★★★

地址:6.pdf

█[9] Mirowski, Piotr, et al. "Learning to navigate in complex environments." arXiv preprint arXiv:1611.03673 (2016). [pdf] ★★★★

地址:3

3.7 艺术

█[1] Mordvintsev, Alexander; Olah, Christopher; Tyka, Mike (2015). "Inceptionism: Going Deeper into Neural Networks". Google Research. [html] (Deep Dream) ★★★★

地址:/2015/06/inceptionism-going-deeper-into-neural.html

█[2] Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. "A neural algorithm of artistic style." arXiv preprint arXiv:1508.06576 (2015). [pdf] (杰出研究,迄今最成功的方法) ★★★★★

地址:6

█[3] Zhu, Jun-Yan, et al. "Generative Visual Manipulation on the Natural Image Manifold." European Conference on Computer Vision. Springer International Publishing, 2016. [pdf] (iGAN) ★★★★

地址:2

█[4] Champandard, Alex J. "Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks." arXiv preprint arXiv:1603.01768 (2016). [pdf] (Neural Doodle) ★★★★

地址:8

█[5] Zhang, Richard, Phillip Isola, and Alexei A. Efros. "Colorful Image Colorization." arXiv preprint arXiv:1603.08511 (2016). [pdf] ★★★★

地址:1

█[6] Johnson, Justin, Alexandre Alahi, and Li Fei-Fei. "Perceptual losses for real-time style transfer and super-resolution." arXiv preprint arXiv:1603.08155 (2016). [pdf] ★★★★

地址:5.pdf

█[7] Vincent Dumoulin, Jonathon Shlens and Manjunath Kudlur. "A learned representation for artistic style." arXiv preprint arXiv:1610.07629 (2016). [pdf] ★★★★

地址:3

█[8] Gatys, Leon and Ecker, et al."Controlling Perceptual Factors in Neural Style Transfer." arXiv preprint arXiv:1611.07865 (2016). [pdf] (control style transfer over spatial location,colour information and across spatial scale) ★★★★

地址:6.pdf

█[9] Ulyanov, Dmitry and Lebedev, Vadim, et al. "Texture Networks: Feed-forward Synthesis of Textures and Stylized Images." arXiv preprint arXiv:1603.03417(2016). [pdf] (纹理生成和风格变化) ★★★★

地址:3

3.8 目标分割 Object Segmentation

█[1] J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation.” in CVPR, 2015. [pdf] ★★★★★

地址:v2.pdf

█[2] L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille. "Semantic image segmentation with deep convolutional nets and fully connected crfs." In ICLR, 2015. [pdf] ★★★★★

地址:5v1.pdf

█[3] Pinheiro, P.O., Collobert, R., Dollar, P. "Learning to segment object candidates." In: NIPS. 2015. [pdf] ★★★★

地址:4v2.pdf

█[4] Dai, J., He, K., Sun, J. "Instance-aware semantic segmentation via multi-task network cascades." in CVPR. 2016 [pdf] ★★★

地址:2v1.pdf

█[5] Dai, J., He, K., Sun, J. "Instance-sensitive Fully Convolutional Networks." arXiv preprint arXiv:1603.08678 (2016). [pdf] ★★★

地址:8v1.pdf