“Student-Research-Training-THU”版本间的差异

来自iCenter Wiki
跳转至： 导航、 搜索
（增加新的内容）
（→‎2018-SRT）
 
（相同用户的48个中间修订版本未显示）
第1行： 第1行：
 
'''SaturnLab-学术活动'''
 
'''SaturnLab-学术活动'''
  
−
=2017年学术活动=
+
=2018-SRT=
  
−
*2017年11月18日
+
* 2018年6月10日
  
−
宋丹丹：
+
郑文勋、柳荫：GPU工作站安装、Pytorch 安装与配置
  
−
*2017年11月11日
+
* 2018年6月3日
−
+
−
闫泽禹：
+
  
−
[x] "Dynamic Routing Between Capsules", S. Sabour, N. Frosst and G.E. Hinton, https://arxiv.org/abs/1710.09829
+
柳荫：  跨层神经网络结构研究
  
−
*2017年11月04日
+
* 2018年5月26日
−
+
−
常嘉辉：GAN
+
  
−
[x] Generative Adversarial Networks: An Overview, https://arxiv.org/abs/1710.07035.
+
郑文勋： [[习得索引]]的研究
  
−
*2017年10月28日
+
* 2018年1月20日
  
−
陆昕：PixelRNN
+
郑文勋： [x] Asynchronous Methods for DRL
−
+
−
[x] Oord, Aaron van den, Nal Kalchbrenner, and Koray Kavukcuoglu. "Pixel recurrent neural networks." arXiv preprint arXiv:1601.06759 (2016).
+
  
−
*2017年10月21日
+
* 2018年1月6日
  
−
冯  杰：DeepST
+
柳荫： [x] Residual Networks Behave Like Ensembles of Relatively Shallow Networks, NIPS 2016. https://arxiv.org/abs/1605.06431.
  
−
[x] Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction, AAAI 2017.
+
=数据管理 =
  
−
议题： AlphaGo Zero
+
==神经网络索引==
  
−
[x] David Silver, Mastering the game of Go without human knowledge, nature 2017
+
[x] A Machine Learning Approach to Databases Indexes, ML Systems Workshop at NIPS 2017.
  
−
[x] Xilinx Inc., Introduction to FPGA Design with Vivado High-Level Synthesis, UG998, 2013.
+
[x] The Case for Learned Index Structures, https://arxiv.org/abs/1712.01208.
  
−
*2017年10月14日
+
==近似树索引 ==
  
−
宋丹丹：
+
[x] A-Tree: A Bounded Approximate Index Structure, sigmod 2018.
−
[x] Matthieu Courbariaux et al., Binarized Neural Networks: Training Neural Networks withWeights and Activations Constrained to +1 or -1, arxiv, 2016.
+
  
−
贺子航：
+
==位图索引==
−
[x] E. Nurvitadhi et al., Accelerating Binarized Neural Networks: Comparison of FPGA, CPU, GPU, and ASIC, International Conference on Field-Programmable Technology (FPT), pp. 77-84, 2016.
+
  
−
陈  震：
+
[x] Athanassoulis, Manos, Zheng Yan, and Stratos Idreos, UpBit: Scalable In-Memory Updatable Bitmap Indexing, sigmod 2016.  
−
[x] Umuroglu, Yaman et al., FINN: A Framework for Fast, Scalable Binarized Neural Network Inference, ACM/SIGDA International Symposium on Field-Programmable Gate Arrays(FPGA), pp.65-74, 2017.
+
  
−
*2017年10月7日
+
=深度学习 =
  
−
柳  荫：
+
==计算机视觉==
−
[x] Huang, Gao, Zhuang Liu, Kilian Q. Weinberger, and Laurens van der Maaten, Densely Connected Convolutional Networks, CVPR 2017.
+
  
−
陈  震：
+
===卷积网络（图像）===
−
[x] Annett Ungethüm et al., Overview on Hardware Optimizations for Database Engines, BTW 2017.
+
  
−
*2017年9月30日
+
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size. https://arxiv.org/abs/1602.07360.
  
−
郑文勋：
+
Xception: Deep Learning with Depthwise Separable Convolutions. https://arxiv.org/abs/1610.02357.
−
[x] Graves, A., Wayne, G. and Danihelka, I., 2014. Neural turing machines. arXiv preprint arXiv:1410.5401.
+
  
−
陈  震：
+
ResNet: Deep residual learning for image recognition, CVPR 2016. https://arxiv.org/abs/1512.03385.
−
[x] Jouppi, N.P. et al., In-Datacenter Performance Analysis of a Tensor Processing Unit, ISCA 2017.
+
  
−
*2017年9月23日
+
GoogLeNet(Inception V3): Going deeper with convolutions, CVPR 2015. https://arxiv.org/abs/1409.4842.
  
−
陈  震：
+
VGG: Very Deep Convolutional Networks for Large Scale Image Recognition, 2014. https://arxiv.org/abs/1409.1556.
−
[x] Jeff. Dean et al., Large scale distributed deep networks. In Advances in neural information processing systems, pp. 1223-1231,  2012.
+
  
−
*2017年5月21日
+
NiN: Network In Network, 2013. https://arxiv.org/abs/1312.4400.
  
−
郑文勋：
 
−
[x] Yu Su et al., In-Situ Bitmaps Generation and Efficient Data Analysis based on Bitmaps, HPDC 2015.
 
  
−
*2017年4月8日
+
===图像分割===
  
−
郑文勋：
+
*object instance segmentation
−
[x] Nguyen, Anh, Jason Yosinski, and Jeff Clune. "Deep neural networks are easily fooled: High confidence predictions for unrecognizable images." CVPR. 2015.
+
  
−
=供选论文清单=
+
[x] Alexander Kirillov, Kaiming He, Ross Girshick, Carsten Rother, Piotr Dollár, Panoptic Segmentation, https://arxiv.org/abs/1801.00868.
  
−
==TensorFlow系列==
+
[x] Ronghang Hu, Piotr Dollár, Kaiming He, Trevor Darrell, Ross Girshick, '''Learning to Segment Every Thing''',  https://arxiv.org/abs/1711.10370.
  
−
DistBelief - large scale distributed deep networks, nips 2012.
+
[x] Xiaolong Wang, Ross Girshick, Abhinav Gupta, Kaiming He, '''Non-local Neural Networks''', https://arxiv.org/abs/1711.07971.
  
−
TensorFlow - A system for large-scale machine learning, OSDI 2016.
+
[x] Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick, '''Mask R-CNN''', ICCV 2017. https://arxiv.org/abs/1703.06870
  
−
TPU - In-Datacenter Performance Analysis of a Tensor Processing Unit, ISCA 2017.
 
  
−
TFX - A TensorFlow-Based Production-Scale Machine Learning Platform, kdd2017.
+
===对象检测===
  
−
==CV系列==
+
*Object_Detection
  
−
Densely Connected Convolutional Networks,CVPR 2017.
+
Feature Pyramid Networks for Object Detection, https://arxiv.org/abs/1612.03144.
  
−
==ASR语音识别==
+
R-FCN: Object Detection via Region-based Fully Convolutional Networks, https://arxiv.org/abs/1605.06409.
  
−
Multichannel Signal Processing with Deep Neural Networks for Automatic Speech Recognition-TASLP-2017
+
PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection, https://arxiv.org/abs/1608.08021.
  
 +
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition, https://arxiv.org/abs/1406.4729.
 +
 +
===立体对象检测===
 +
 +
*3D_OD
 +
 +
Voting for Voting in Online Point Cloud Object Detection
 +
 +
3D object proposal for object class detection
 +
 +
3D Fully Convolutional Network for Vehicle Detection in Point Cloud
 +
 +
Vehicle Detection from 3D Lidar Using Fully Convolutional Network
 +
 +
Multi-View 3D Object Detection Network for Autonomous Driving
 +
 +
==语音识别==
 +
 +
*Speech Recognition
 +
 +
[x] State-of-the-art Speech Recognition With Sequence-to-Sequence Models, https://arxiv.org/abs/1712.01769.
 +
 +
[z] Recent progresses in deep learning based acoustic models, 2017.
 +
 +
[z] Multichannel Signal Processing with Deep Neural Networks for Automatic Speech Recognition, TASLP 2017.
 +
 +
[z] DeepSpeech3 Exploring Neural Transducers for End-to-End Speech Recognition. https://arxiv.org/abs/1707.07413.
 +
 +
[z] Cold Fusion: Training Seq2Seq Models Together with Language Models, 2017. https://arxiv.org/abs/1708.06426.
 +
 +
 +
==工具==
 +
===TensorFlow系列===
 +
 +
DistBelief - large scale distributed deep networks, NIPS 2012.
 +
 +
TensorFlow - A system for large-scale machine learning, OSDI 2016.
 +
 +
TPU - In-Datacenter Performance Analysis of a Tensor Processing Unit, ISCA 2017.
  
−
==XXXX==
+
TFX - A TensorFlow-Based Production-Scale Machine Learning Platform, kdd 2017.
  
 +
==选择==
  
−
[Quasi-Recurrent Neural Networks](https://arxiv.org/abs/1611.01576)
+
[1] Quasi-Recurrent Neural Networks,(https://arxiv.org/abs/1611.01576)
  
−
[Training RNNs as Fast as CNNs](https://arxiv.org/abs/1709.02755)
+
[2] Training RNNs as Fast as CNNs, (https://arxiv.org/abs/1709.02755)
  
−
[Semi-Supervised Classification with Graph Convolutional Networks](https://arxiv.org/abs/1609.02907)
+
[3] Semi-Supervised Classification with Graph Convolutional Networks, (https://arxiv.org/abs/1609.02907)
  
−
[A Survey on Transfer Learning](http://www3.ntu.edu.sg/home/sinnopan/publications/TLsurvey_0822.pdf)
+
[4] A Survey on Transfer Learning, (http://www3.ntu.edu.sg/home/sinnopan/publications/TLsurvey_0822.pdf)
  
−
[How transferable are features in deep neuralnetworks?](https://arxiv.org/abs/1411.1792)
+
[5] How transferable are features in deep neuralnetworks? (https://arxiv.org/abs/1411.1792)
  
−
[Progressive Neural Networks](https://arxiv.org/abs/1606.04671)
+
[6] Progressive Neural Networks, (https://arxiv.org/abs/1606.04671)
  
−
[One-Shot Learning of Object Categories](http://vision.stanford.edu/documents/Fei-FeiFergusPerona2006.pdf)
+
[7] One-Shot Learning of Object Categories](http://vision.stanford.edu/documents/Fei-FeiFergusPerona2006.pdf)
  
−
[One-shot Learning with Memory-Augmented Neural Networks](https://arxiv.org/abs/1605.06065)
+
[8] One-shot Learning with Memory-Augmented Neural Networks,(https://arxiv.org/abs/1605.06065)
  
−
[Auto-Encoding Variational Bayes](https://arxiv.org/abs/1312.6114)
+
[9] Auto-Encoding Variational Bayes,(https://arxiv.org/abs/1312.6114)
  
−
[Autoencoding beyond pixels using a learned similarity metric](https://arxiv.org/abs/1512.09300)
+
[10] Autoencoding beyond pixels using a learned similarity metric,(https://arxiv.org/abs/1512.09300)

2018年8月22日 (三) 11:50的最后版本

SaturnLab-学术活动

2018-SRT

  • 2018年6月10日

郑文勋、柳荫：GPU工作站安装、Pytorch 安装与配置

  • 2018年6月3日

柳荫： 跨层神经网络结构研究

  • 2018年5月26日

郑文勋： 习得索引的研究

  • 2018年1月20日

郑文勋： [x] Asynchronous Methods for DRL

  • 2018年1月6日

柳荫： [x] Residual Networks Behave Like Ensembles of Relatively Shallow Networks, NIPS 2016. https://arxiv.org/abs/1605.06431.

数据管理

神经网络索引

[x] A Machine Learning Approach to Databases Indexes, ML Systems Workshop at NIPS 2017.

[x] The Case for Learned Index Structures, https://arxiv.org/abs/1712.01208.

近似树索引

[x] A-Tree: A Bounded Approximate Index Structure, sigmod 2018.

位图索引

[x] Athanassoulis, Manos, Zheng Yan, and Stratos Idreos, UpBit: Scalable In-Memory Updatable Bitmap Indexing, sigmod 2016.

深度学习

计算机视觉

卷积网络（图像）

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size. https://arxiv.org/abs/1602.07360.

Xception: Deep Learning with Depthwise Separable Convolutions. https://arxiv.org/abs/1610.02357.

ResNet: Deep residual learning for image recognition, CVPR 2016. https://arxiv.org/abs/1512.03385.

GoogLeNet(Inception V3): Going deeper with convolutions, CVPR 2015. https://arxiv.org/abs/1409.4842.

VGG: Very Deep Convolutional Networks for Large Scale Image Recognition, 2014. https://arxiv.org/abs/1409.1556.

NiN: Network In Network, 2013. https://arxiv.org/abs/1312.4400.


图像分割

  • object instance segmentation

[x] Alexander Kirillov, Kaiming He, Ross Girshick, Carsten Rother, Piotr Dollár, Panoptic Segmentation, https://arxiv.org/abs/1801.00868.

[x] Ronghang Hu, Piotr Dollár, Kaiming He, Trevor Darrell, Ross Girshick, Learning to Segment Every Thing, https://arxiv.org/abs/1711.10370.

[x] Xiaolong Wang, Ross Girshick, Abhinav Gupta, Kaiming He, Non-local Neural Networks, https://arxiv.org/abs/1711.07971.

[x] Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick, Mask R-CNN, ICCV 2017. https://arxiv.org/abs/1703.06870


对象检测

  • Object_Detection

Feature Pyramid Networks for Object Detection, https://arxiv.org/abs/1612.03144.

R-FCN: Object Detection via Region-based Fully Convolutional Networks, https://arxiv.org/abs/1605.06409.

PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection, https://arxiv.org/abs/1608.08021.

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition, https://arxiv.org/abs/1406.4729.

立体对象检测

  • 3D_OD

Voting for Voting in Online Point Cloud Object Detection

3D object proposal for object class detection

3D Fully Convolutional Network for Vehicle Detection in Point Cloud

Vehicle Detection from 3D Lidar Using Fully Convolutional Network

Multi-View 3D Object Detection Network for Autonomous Driving

语音识别

  • Speech Recognition

[x] State-of-the-art Speech Recognition With Sequence-to-Sequence Models, https://arxiv.org/abs/1712.01769.

[z] Recent progresses in deep learning based acoustic models, 2017.

[z] Multichannel Signal Processing with Deep Neural Networks for Automatic Speech Recognition, TASLP 2017.

[z] DeepSpeech3 Exploring Neural Transducers for End-to-End Speech Recognition. https://arxiv.org/abs/1707.07413.

[z] Cold Fusion: Training Seq2Seq Models Together with Language Models, 2017. https://arxiv.org/abs/1708.06426.


工具

TensorFlow系列

DistBelief - large scale distributed deep networks, NIPS 2012.

TensorFlow - A system for large-scale machine learning, OSDI 2016.

TPU - In-Datacenter Performance Analysis of a Tensor Processing Unit, ISCA 2017.

TFX - A TensorFlow-Based Production-Scale Machine Learning Platform, kdd 2017.

选择

[1] Quasi-Recurrent Neural Networks,(https://arxiv.org/abs/1611.01576)

[2] Training RNNs as Fast as CNNs, (https://arxiv.org/abs/1709.02755)

[3] Semi-Supervised Classification with Graph Convolutional Networks, (https://arxiv.org/abs/1609.02907)

[4] A Survey on Transfer Learning, (http://www3.ntu.edu.sg/home/sinnopan/publications/TLsurvey_0822.pdf)

[5] How transferable are features in deep neuralnetworks? (https://arxiv.org/abs/1411.1792)

[6] Progressive Neural Networks, (https://arxiv.org/abs/1606.04671)

[7] One-Shot Learning of Object Categories](http://vision.stanford.edu/documents/Fei-FeiFergusPerona2006.pdf)

[8] One-shot Learning with Memory-Augmented Neural Networks,(https://arxiv.org/abs/1605.06065)

[9] Auto-Encoding Variational Bayes,(https://arxiv.org/abs/1312.6114)

[10] Autoencoding beyond pixels using a learned similarity metric,(https://arxiv.org/abs/1512.09300)

取自“http://wiki.icenter.tsinghua.edu.cn/icenterwiki/index.php?title=Student-Research-Training-THU&oldid=47877”