一、書籍
Deep learning (2015)
作者:Bengio
下載地址:http://www.deeplearningbook.org/
二、理論
1.在神經網絡中提取知識
Distilling the knowledge in a neural network
作者:G. Hinton et al.
2.深度神經網絡很易受騙:高信度預測無法識別的圖片
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
作者:A. Nguyen et al.
3.深度神經網絡特徵的可遷移性如何?
How transferable are features in deep neural networks? (2014),
作者:J. Yosinski et al.
4.深挖卷積網絡的各個細節
Return of the Devil in the Details: Delving Deep into Convolutional Nets (2014)
作者:K. Chatfield et al.
5.爲什麼無監督預訓練對深度學習有幫助?
Why does unsupervised pre-training help deep learning (2010)
作者:D. Erhan et al. (Bengio)
6.理解訓練深度前饋神經網絡的難點
Understanding the difficulty of training deep feedforward neural networks (2010)
作者:X. Glorot and Y. Bengio
三、優化/網絡結構
簡介:本部分從文獻7到文獻14爲神經網絡優化的一些方法,尤其是文獻7的批歸一化更是在業界產生巨大的影響;文獻15到文獻22爲網絡結構的變化,包括全卷積神經網絡等。這些參考文獻都是非常具有參考價值的乾貨!
7.Batch Normalization 算法:通過減少內部協變量轉化加速深度網絡的訓練(推薦)
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (2015)
作者:S. Loffe and C. Szegedy (Google)
8.Dropout:一個預防神經網絡過擬合的簡單方式
Dropout: A simple way to prevent neural networks from overfitting (2014)
作者:N. Srivastava et al. (Hinton)
9.Adam:一個隨機優化的方法
Adam: A method for stochastic optimization (2014)
作者:D. Kingma and J. Ba
10.論深度學習領域初始化和動量的重要性
On the importance of initialization and momentum in deep learning (2013)
作者:I. Sutskever et al. (Hinton)
11.使用 Dropconnect 的神經網絡正則化
Regularization of neural networks using dropconnect (2013)
作者:L. Wan et al. (LeCun)
12.超參數最優化的隨機搜索
Random search for hyper-parameter optimization (2012)
作者:J. Bergstra and Y. Bengio
13.圖像識別中的深度殘差學習
Deep residual learning for image recognition (2016)
作者:K. He et al. (Microsoft)
14.用於物體精準檢測和分割的基於區域的卷積網絡
Region-based convolutional networks for accurate object detection and segmentation (2016)
作者:R. Girshick et al.(Microsoft)
15.更深的卷積網絡
Going deeper with convolutions (2015)
作者:C. Szegedy et al. (Google)
16.快速 R-CNN 網絡
Fast R-CNN (2015)
作者: R. Girshick (Microsoft)
16.更快速的 R-CNN 網絡:使用區域網絡的實時物體檢測
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (2015)
作者: S. Ren et al.
17.用於語義分割的全卷積神經網絡
Fully convolutional networks for semantic segmentation (2015)
作者:J. Long et al.
18.大規模圖像識別的深度卷積網絡
Very deep convolutional networks for large-scale image recognition (2014)
作者:K. Simonyan and A. Zisserman
19.OverFeat:使用卷積網絡融合識別、本地化和檢測
OverFeat: Integrated recognition, localization and detection using convolutional networks (2014)
作者:P. Sermanet et al.(LeCun)
20.可視化以及理解卷積網絡
Visualizing and understanding convolutional networks (2014)
作者:M. Zeiler and R. Fergus
21.Maxout 網絡
Maxout networks (2013)
作者:I. Goodfellow et al. (Bengio)
22.Network In Network 深度網絡架構
Network in network (2013)
作者:M. Lin et al.
四、圖像
1.使用卷積神經網絡在自然環境下閱讀文本
Reading text in the wild with convolutional neural networks (2016)
作者:M. Jaderberg et al. (DeepMind)
2.Imagenet 大規模視覺識別挑戰賽
Imagenet large scale visual recognition challenge (2015)
作者:O. Russakovsky et al.
3.DRAW:一個用於圖像生成的循環神經網絡
DRAW: A recurrent neural network for image generation (2015)
作者:K. Gregor et al.
4.對精確的物體檢測和語義切割更爲豐富的特徵分層
Rich feature hierarchies for accurate object detection and semantic segmentation (2014)
作者: R. Girshick et al.
5.使用卷積神經網絡學習和遷移中層圖像表徵
Learning and transferring mid-Level image representations using convolutional neural networks (2014)
作者:M. Oquab et al.
6.DeepFace:在面部驗證任務中接近人類表現
DeepFace: Closing the Gap to Human-Level Performance in Face Verification (2014)
作者:Y. Taigman et al. (Facebook)
五、視頻 / 人類行爲
1.利用卷積神經網絡進行大規模視頻分類(2014)
Large-scale video classification with convolutional neural networks (2014)
作者:A. Karpathy et al. (FeiFei)
2.DeepPose:利用深度神經網絡評估人類姿勢
DeepPose: Human pose estimation via deep neural networks (2014)
作者:A. Toshev and C. Szegedy (Google)
3.用於視頻中動作識別的雙流卷積網絡
Two-stream convolutional networks for action recognition in videos (2014)
作者:K. Simonyan et al.
4.用於人類動作識別的 3D 卷積神經網絡(這篇文章針對連續視頻幀進行處理,是個不錯的)
3D convolutional neural networks for human action recognition (2013)
作者:S. Ji et al.
5.帶有改進軌跡的動作識別
Action recognition with improved trajectories (2013)
作者:H. Wang and C. Schmid
6.用獨立子空間分析,學習用於動作識別的等級恆定的時空特徵
Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis (2011)
作者:Q. Le et al
六、自然語言處理
1.用 RNN 編碼——解碼器學習短語表徵,實現統計機器翻譯
Learning phrase representations using RNN encoder-decoder for statistical machine translation (2014)
作者:K. Cho et al.(Bengio)
2.一個爲句子建模的卷積神經網絡
A convolutional neural network for modelling sentences (2014)
作者:N. Kalchbrenner et al.
3.用於句子分類的卷積神經網絡
Convolutional neural networks for sentence classification (2014)
作者:Y. Kim
4.斯坦福 coreNLP 自然語言處理工具
The stanford coreNLP natural language processing toolkit (2014)
作者:C. Manning et al.
5.基於情感樹庫應用於情感組合研究的遞歸深度網絡模型
Recursive deep models for semantic compositionality over a sentiment treebank (2013)
作者:R. Socher et al.
6.基於語言模型的循環神經網絡
Recurrent neural network based language model (2010)
作者:T. Mikolov et al.
7.自動語音識別:一種深度學習的方法
Automatic Speech Recognition - A Deep Learning Approach (Book, 2015)
作者:D. Yu and L. Deng (Microsoft)
8.使用深度循環網絡進行語音識別
Speech recognition with deep recurrent neural networks (2013)
作者:A. Graves (Hinton)
9.基於上下文預訓練的深度神經網絡在大規模詞表語音識別中的應用
Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition (2012)
作者:G. Dahl et al.
10.使用深度信念網絡進行聲學建模
Acoustic modeling using deep belief networks (2012)
作者:A. Mohamed et al. (Hinton)
七、無監督學習
1.自編碼變量貝葉斯
Auto-Encoding Variational Bayes (2013)
作者:D. Kingma and M. Welling
2.用大規模無監督學習搭建高水平特徵
Building high-level features using large scale unsupervised learning (2013)
作者:Q. Le et al.
3.無監督特徵學習中單層網絡分析
An analysis of single-layer networks in unsupervised feature learning (2011)
作者:A. Coates et al.
4.堆棧降噪解碼器:在本地降噪標準的深度網絡中學習有用的表徵
Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion (2010)
作者:P. Vincent et al. (Bengio)
5.訓練受限波茲曼機的實踐指南
A practical guide to training restricted boltzmann machines (2010)
作者:G. Hinton
八、開源架構
1.TensorFlow:異構分佈式系統上的大規模機器學習
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems (2016)
作者:M. Abadi et al. (Google)
2.Theano:一個針對快速計算數學表達公式的Python框架
Theano: A Python framework for fast computation of mathematical expressions
作者:R. Al-Rfou et al. (Bengio)
3.MatConvNet: 針對matlab 的卷積神經網絡
MatConvNet: Convolutional neural networks for matlab (2015)
作者:A. Vedaldi and K. Lenc
4.Caffe:快速特徵嵌入的卷積結構
Caffe: Convolutional architecture for fast feature embedding (2014)
作者: Y. Jia et al.
九、2016最新論文
1.對立學習推論
Adversarially Learned Inference (2016)
作者:V. Dumoulin et al.
2.理解卷積神經網絡
Understanding Convolutional Neural Networks (2016)
作者:J. Koushik
3.SqueezeNet 模型:達到 AlexNet 水平的準確率,卻使用縮減 50 倍的參數以及< 1MB 的模型大小
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 1MB model size (2016)
作者:F. Iandola et al.
4.學習搭建問答神經網絡
Learning to Compose Neural Networks for Question Answering (2016)
作者:J. Andreas et al.
5.用深度學習和大規模數據蒐集,學習眼手協調的機器人抓取
Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection (2016)(Google)
作者:S. Levine et al.
6.將人隔離在外:貝葉斯優化算法回顧
Taking the human out of the loop: A review of bayesian optimization (2016)
作者:B. Shahriari et al.
7.Eie:壓縮神經網絡的高效推理引擎
Eie: Efficient inference engine on compressed deep neural network (2016)
作者:S. Han et al.
8.循環神經網絡的自適性計算時間
Adaptive Computation Time for Recurrent Neural Networks (2016)
作者:A. Graves
9.像素循環神經網絡
Pixel Recurrent Neural Networks (2016)
作者:A. van den Oord et al. (DeepMind)
10.LSTM:一場搜索空間的奧德賽之旅
LSTM: A search space odyssey (2016)
作者:K. Greff et al.
---------------------
作者:深度學習思考者
來源:CSDN
原文:https://blog.csdn.net/u010402786/article/details/51682917
版權聲明:本文爲博主原創文章,轉載請附上博文鏈接!