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)

Student-Research-Training-THU

目录