论文原文解读汇总(持续更新中)

以下是自己对一些论文原文的解读:
机器学习:
《XGBoost: A Scalable Tree Boosting System》
《CatBoost:gradient boosting with categorical features support》-2018
《LightGBM:A Highly Efficient Gradient Boosting Decision Trees》
主流剪枝算法原理与代码实现汇总
《Improved Use of Continuous Attributes in C4.5》

NLP:
《Latent Dirichlet Allocation》-2003
《Probabilistic Latent Semantic Indexing》

神经网络论文解读：
《A LOGICAL CALCULUS OF THE IDEAS IMMANENT IN NERVOUS ACTIVITY》(神经网络鼻祖，符号生僻，基本没法阅读)
《Learning representations by back-propagating errors》
《finding Structure in time》
《Backpropagation Through Time:What it Does and How to Do it》

权值更新的算法文章：
比较重要的一篇综述是：
http://ruder.io/optimizing-gradient-descent/index.html

《Batch Normalization:Accelerating Deep Network Training by Reducing Internal Covariate Shift》（Batch Normalization原文解读）

《On the momentum term in gradient descent learning algorithms》(Momentum原文解读，这篇是讲物理机械振荡的)

《A method for unconstrained convex minimization problem with the rate of convergence》(Nesterov’s Momentum原文)
《ADAM: A METHOD FOR STOCHASTIC OPTIMIZATION》(adam原文)
《ADADELTA: AN ADAPTIVE LEARNING RATE METHOD》(adadelta原文)
《Adaptive Subgradient Methods for Online Learning and Stochastic Optimization》(adagrad原文)
《Learning Long-Term Dependencies with Gradient Descent is Difficult》(首次提出RNN梯度消失的文章)

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling(GRU单元)

#----------------------------------------------------------------------------------
YOLO系列（还没开始）
YOLOv1
You Only Look Once:Unified,Real-Time Object Detection

YOLOv2:
YOLO9000:Better,Faster,Stronger

YOLOv3:
YOLOv3:An Incremental Improvement
#----------------------------------------------------------------------------------
Inception系列（还没开始）
Inception v1:
Going deeper with convolutions

Inception v2:
Rethinking the Inception Architecture for Computer Vision

Inception v3:
Xception:Deep Learning with Depthwise Separable Convolutions

Inception v4:
Inception-v4,Inception-ResNet and the Impact of Residual Connections on Learning

#----------------------------------------------------------------------------------
DeepID系列(还没开始）
Deep ID1:
Deep Learning Face Representation from Predicting 10,000 Classes

DeepID2:
Deep Learning Face Representation by Joint Identification-Verification

DeepID2+:
Deeply learned face representations are spars,selective,and robust

DeepID3:
DeepID3:Face Recognition with Very Deep Neural Networks
#----------------------------------------------------------------------------------
LeNet：
Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner（1998）: Gradient-based
learning applied to document recognition. Proceedings of the IEEE 86,
11 (November 1998), 2278 – 2324.

AlexNet
Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton（2012）:
ImageNet Classification with Deep Convolutional Neural Networks.
In F. Pereira, C. J. C. Burges, L. Bottou, & K. Q. Weinberger, eds.
Advances in Neural Information Processing Systems 25. Curran
Associates, Inc., 1097 – 1105

ResNet：
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun（2015）:
Deep Residual Learning for Image Recognition. arXiv:1512.03385 [cs]
(December 2015)

Vgg：
Karen Simonyan and Andrew Zisserman（2014）: Very Deep
Convolutional Networks for Large-Scale Image Recognition.
arXiv:1409.1556 [cs] (September 2014)

GoogleNet:
Christian Szegedy et al（2015）: Going Deeper With Convolutions. In
The IEEE Conference on Computer Vision and Pattern Recognition
(CVPR)

RCNN
Ross Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik（2014）:
Rich Feature Hierarchies for Accurate Object Detection and Semantic
Segmentation. In 580 – 587.

Faster RCNN:
Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun（2015）: Faster
R-CNN: Towards Real-Time Object Detection with Region Proposal
Networks. In C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, & R.
Garnett, eds. Advances in Neural Information Processing Systems 28.
Curran Associates, Inc., 91 – 99.

FCN
Jonathan Long, Evan Shelhamer, and Trevor Darrell（2015）: Fully
Convolutional Networks for Semantic Segmentation. In The IEEE
Conference on Computer Vision and Pattern Recognition (CVPR).

NIC
Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan
（2015）: Show and Tell: A Neural Image Caption Generator. In The
IEEE Conference on Computer Vision and Pattern Recognition
(CVPR)

DCGAN
Alec Radford, Luke Metz, and Soumith Chintala（2015）: Unsupervised
Representation Learning with Deep Convolutional Generative
Adversarial Networks. arXiv:1511.06434 [cs] (November 2015)

SegNet:
Vijay Badrinarayanan, Kendall, and Roberto Cipolla（2015）: SegNet:
A Deep Convolutional Encoder-Decoder Architecture for Image
Segmentation. arXiv preprint arXiv:1511.00561 (2015).

注意，卷积层会消耗大量的时间，vgg工程师们都很爱用

人工智能论文合集
这个最后看
Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures

下面一些原文还没阅读:

Learning representations by back-propagating errors
1998《Gradient-Based Learning Applied to Documnet Recognition》
2006《Reducing the Dimensionality of Data with Neural Networks》
2012《ImageNet Classification with Deep Convolutional Neural Networks》
2013.11《Visualizing and Understanding Convolutional Networks》(CNN可视化工具)
2013.12《OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks》
<DeepFace: Closing the Gap to Human-Level Performance in Face Verification>
<Spatial Transformer Networks>
Serial Order:A Parallel Distributed Processing Approach(这个文章是RNN成型前的文章)

<Highway Neiworks>
<Recurrent Highway Networks>
<The Vanishing Gradient Problem>(For the ppt of this lecture click here)
<The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions>
<Learning Long-Term Dependencies with Gradient Descent is difficult>

<Implement binary addition with a non-linear RNN>
<Bidirectional recurrent neural networks>
<Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation>
<On the difficulty of training recurrent neural networks>
<Recurrent Nets that Time and Count>
<Bidirectional Long Short-Term Memory Networks for Predicting the Subcellular Localization of Eukaryotic Proteins>
<Efficient Processing of Deep Neural Networks:A Tutorial and Survey>
<Long Short-Term Memory>(不要去阅读，符号古怪 )
<Finding Structure in Time>(不要去阅读，符号古怪 )
How to Implement a Simple RNN
Reducing the Dimensionality of Data with Neural networks
Gradient-Based Learning Applied to Document Recognition

Network In Network
Very Deep Convolutional Networks For Large-Scale Image Recognition(VGG16-VGG19)
DeePose:Human Pose Estimation via Deep Neural Networks

【ICLR 2017】SqueezeNet AlexNet-level accuracy with 50x fewer parameters and 0.5MB model size

Fast R-CNN
Faster R-CNN:Towards Real-Tme Object Detection with Region Proposal Networks
Generative Adversarial Nets
Understanding the difficulty of training deep feedforward neural networks
Densely Connected Convolutional Networks(DenseNet)

Neural Networks and Physical Systems with Emergent Collective Computational Abilities