deep learning
来源:互联网 发布:和隆优化怎么样 编辑:程序博客网 时间:2024/05/16 05:45
Surveys
1) Survey on representation learning: http://arxiv.org/pdf/1206.5538.pdf
2) Building Machines That Learn and Think Like People: http://arxiv.org/abs/1604.00289
Transfer Leraning
3) Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning: http://arxiv.org/pdf/1511.06342v4.pdf
4) Progressive Neural Networks: https://arxiv.org/pdf/1606.04671v3.pdf
5) Distilling the knowledge in a Neural Network: https://www.cs.toronto.edu/~hinton/absps/distillation.pdf
6) Policy distillation: http://arxiv.org/pdf/1511.06295v2.pdf
(Inverse) Reinforcement Leraning
7) Deep Inverse Reinforcement Learning: http://www.cs.utexas.edu/~sniekum/classes/RLFD-F15/papers/Wulfmeier15.pdf
8) An actor-critic algorithm for sequence prediction: https://arxiv.org/pdf/1607.07086v2.pdf
9) professor forcing: a new algorithm for training recurrent networks
Encoder-decoder && adversarial learning
10) Generative Adversarial Nets: http://datascienceassn.org/sites/default/files/Generative%20Adversarial%20Nets.pdf
11) InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets: http://arxiv.org/abs/1606.03657
12) Auto-Encoding Variational Bayes: http://arxiv.org/abs/1312.6114
13) Adversarially learned Inference: https://arxiv.org/pdf/1606.00704v1.pdf
14) Unsupervised representation learning with deep convolutional generative adversarial networks
15) Adversarial feature learning
Attention and related
16) Show, Attend and Tell: Neural Image Caption Generation with Visual Attention: http://jmlr.org/proceedings/papers/v37/xuc15.pdf
17) DRAW: A Recurrent Neural Network For Image Generation: https://arxiv.org/pdf/1502.04623v2.pdf
18) Attend, Infer, Repeat: Fast Scene Understanding with Generative Models: http://arxiv.org/abs/1603.08575
19) Recurrent models of visual attention
(Visual) question answer
20) Learning to Compose Neural Networks for Question Answering: http://arxiv.org/pdf/1601.01705.pdf
New articeture of CNN
21) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks: https://arxiv.org/pdf/1506.01497.pdf
22) Residual Network: https://arxiv.org/pdf/1512.03385v1.pdf
23) Identity mapping: https://arxiv.org/pdf/1603.05027.pdf
24) Highway network: https://arxiv.org/pdf/1505.00387v2.pdf
25) Deep Networks with stochastic depth: https://arxiv.org/pdf/1603.09382v3.pdf
RNN/LSTM/Vedio
26) Pixel Recurrent Neural Networks: https://arxiv.org/pdf/1601.06759v3.pdf
27) Structual-RNN: Deep learning on spatio-Temporal graphs
28) Leraning to forget: continual prediction with LSTM
29) Training Recurrent Neural Networks by diffusion
30) Unsupervised learning of video representations using LSTMs
31) Describing videos by exploiting temporal structure
32) Delving deeper into convolutional networks for learning video representations
0 0
- Deep learning
- deep learning
- 【deep learning】
- Deep Learning
- Deep Learning
- deep learning
- Deep learning
- deep learning
- Deep Learning
- Deep Learning
- 【deep learning】
- deep learning
- deep learning
- Deep Learning
- Deep Learning
- Deep Learning
- Deep Learning
- Deep Learning
- JavaScript形参和实参
- 异常处理
- 托管堆和垃圾回收
- IT求职感悟
- bzoj4318 OSU! 概率DP
- deep learning
- [BZOJ1195] [HNOI2006]最短母串(状压dp)
- C与CUDA混合编程的配置问题
- Java:单例模式的七种写法
- Linux下c和cuda混合编译,并生成动态链接库.so和使用
- extern "c"用法解析
- nvcc gcc g++混合编译器编程
- Lambda表达式
- 泛型接口