爱可可老师一周论文精选(2019.1.5)

No 1. 【博士论文:统计与优化——统计学习算法的计算保障】
No 2. 【LSTM的大批量(Large-Batch)训练】
No 3. 【博士论文:元监督视觉学习】
No 4. 《SageDB: A Learned Database》
No 5. 《Neural Model-Based Reinforcement Learning for Recommendation》
No 6. 《Pay Less Attention with Lightweight and Dynamic Convolutions》
No 7. 《Recurrent Neural Networks for Time Series Forecasting》
No 8. 《InstaGAN: Instance-aware Image-to-Image Translation》
No 9. 《The Matrix Calculus You Need For Deep Learning》
No 10. 《EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning》
No 11. 《Looking for ELMo's friends: Sentence-Level Pretraining Beyond Language Modeling》
No 12. 《Visualizing Deep Similarity Networks》
No 13. 《A Comprehensive Survey on Graph Neural Networks》
No 14. 《Improving Generalization and Stability of Generative Adversarial Networks》
No 15. 《Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization》
No 16. 《Multi-class Classification without Multi-class Labels》
No 17. 《BA-Net: Dense Bundle Adjustment Networks》
No 18. 《Temporal Difference Variational Auto-Encoder》
No 19. 《Dynamic Planning Networks》
No 20. 《Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks》
No 21. 《Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and Algorithms》
No 22. 《3D Convolution on RGB-D Point Clouds for Accurate Model-free Object Pose Estimation》
No 23. 《Machine learning in resting-state fMRI analysis》
No 24. 《Finger-GAN: Generating Realistic Fingerprint Images Using Connectivity Imposed GAN》
No 25. 《KnockoffGAN: Generating Knockoffs for Feature Selection using Generative Adversarial Networks》
No 26. 《Multiple Sclerosis Lesion Inpainting Using Non-Local Partial Convolutions》
No 27. 《Predicting Aircraft Trajectories: A Deep Generative Convolutional Recurrent Neural Networks Approach》
No 28. 《RegNet: Learning the Optimization of Direct Image-to-Image Pose Registration》
No 29. 《Lagging Inference Networks and Posterior Collapse in Variational Autoencoders》
No 30. 《A Theoretical Analysis of Deep Q-Learning》

发表评论

电子邮件地址不会被公开。 必填项已用*标注