整理一下要读的已读的书籍论文,加粗为还没有读的
神经网络通用理论
优化方法,正则化,训练技巧等
- Understanding the difficulty of training deep feedforward neural networks (AISTATS 2010)
- Dropout: A Simple Way to Prevent Neural Networks from Overfitting (JMLR 2014)
- Adam: A Method for Stochastic Optimization (ICLR 2015)
- An overview of gradient descent optimization algorithms (arXiv 2017)
- The Shattered Gradients Problem: If resnets are the answer, then what is the question? (ICML 2017)
- Bag of Tricks for Image Classification with Convolutional Neural Networks (arXiv 2018)
自然语言处理类
word embedding
- Efficient Estimation of Word Representations in Vector Space (aiXiv 2013)
- Distributed Representations of Words and Phrases and their Compositionality (NIPS 2013)
- Word2vec Parameter Learning Explained (arXiv 2014)
- GloVe: Global Vectors for Word Representation (EMNLP 2014)
- Improving Distributional Similarity with Lessons Learned from Word Embeddings (TACL 2015)
- Evaluation methods for unsupervised word embeddings (EMNLP 2015)
- A Latent Variable Model Approach to PMI-based Word Embeddings (TACL 2016)
- Linear Algebraic Structure of Word Senses, with Applications to Polysemy (TACL 2018)
- On the Dimensionality of Word Embedding (NIPS 2018)
计算机视觉
CNN架构
- (LeNet) Gradient Based Learning Applied to Document Recognition (PROC OF THE IEEE 1998)
- (AlexNet) ImageNet Classification with Deep Convolutional Neural Networks.
- Network In Network (NIPS 2012)
- (VGGNet) Very Deep Convolutional Networks for Large-Scale Image Recognition (ICLR 2015)
- (GoogLeNetV1) Going deeper with convolutions (CVPR 2015)
- (GoogLeNetV2) Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (ICML 2015)
- (GoogLeNetV3) Rethinking the Inception Architecture for Computer Vision (CVPR 2016)
- (GoogLeNetV4) Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (AAAI 2017)
- Highway Networks (ICML Workshop 2015)
- (ResNet)Deep Residual Learning for Image Recognition (CVPR 2016)
- (ResNetV2) Identity Mappings in Deep Residual Networks (ECCV 2016)
- (DenseNet) Densely Connected Convolutional Networks (CVPR 2017)
- Xception: Deep Learning with Depthwise Separable Convolutions (CVPR 2017)
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision (arXiv 2017)
- MobileNetV2: Inverted Residuals and Linear Bottlenecks (CVPR 2018)
- Squeeze-and-Excitation Networks (CVPR 2018)
- ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile (CVPR 2018)
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design (ECCV 2018)
目标检测
- (R-CNN) Rich feature hierarchies for accurate object detection and semantic segmentation (CVPR 2014)
- Fast R-CNN (ICCV 2015)
- (Faster R-CNN) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (NIPS 2015)
- (SSD) SSD: Single Shot MultiBox Detector (ECCV 2016)
- (SPPNet) Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition (TPAMI 2015)
- (YOLOV1) You Only Look Once: Unified, Real-Time Object Detection (CVPR 2016)
- (YOLOV2) YOLO9000: Better, Faster, Stronger (CVPR 2017)
- (YOLOV3) YOLOv3: An Incremental Improvement (arXiv 2018)
- Feature Pyramid Networks for Object Detection (CVPR 2017)
- Focal Loss for Dense Object Detection (ICCV 2017)
- Mask R-CNN (ICCV 2017)
可视化与可解释性
- Visualizing and Understanding Convolutional Networks (ECCV 2014)
- Understanding Deep Image Representations by Inverting Them (CVPR 2015)
生成模型
Generative Adversarial Network
- Generative Adversarial Network (NIPS 2014)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (arXiv 2016)
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets (NIPS 2016)
- Adversarial Feature Learning (ICLR 2017)
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (ICCV 2017)
- Wasserstein GAN (ICML 2017)
- (ACGAN) Conditional Image Synthesis With Auxiliary Classifier GANs (ICML 2017)
- Boundary-Seeking Generative Adversarial Networks (ICLR 2018)
VAE
- Auto-Encoding Variational Bayes
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Recent Advances in Autoencoder-Based Representation Learning
- Hyperspherical Variational Auto-Encoders
- VAE with a VampPrior
- beta-VAE: Learning basic visual concepts with a constrained variational framework
- InfoVAE: Information maximizing variational autoencoders
- Variational inference of disentangled latent concepts from unlabeled observations
- Information constraints on auto-encoding variational bayes
- Structured disentangled representations
- PixelVAE: A latent variable model for natural images
- Learning hierarchical features from deep generative models
- Semi-supervised learning with deep generative models
- PixelGAN autoencoders
- GO GRADIENT FOR EXPECTATION-BASED OBJECTIVES
- Neural Variational Inference and Learning in Belief Networks
张量应用
- Tensor Decompositions and Applications. Tamara G. Kolda, Brett W. Bader. SIAM REVIEW
- Tensor Decompositions for Learning Latent Variable Models. JMLR
阅读计划
原文:https://www.cnblogs.com/cuhm/p/10563200.html