爱可可老师一周论文精选(2019.7.13)

No 1. 《What graph neural networks cannot learn: depth vs width》
No 2. 【用无监督词向量从材料科学文献中获取潜在知识】
No 3. 【用无监督数据增扩推进半监督学习】
No 4. 《Adaptive Attention Span in Transformers》
No 5. 《Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty》
No 6. 《Slim-CNN: A Light-Weight CNN for Face Attribute Prediction》
No 7. 《Neural Networks, Hypersurfaces, and Radon Transforms》
No 8. 《Multivariate Time Series Imputation with Variational Autoencoders》
No 9. 《Discovering Communities of Community Discovery》
No 10. 《Large Scale Adversarial Representation Learning》
No 11. 《DeepMRSeg: A convolutional deep neural network for anatomy and abnormality segmentation on MR images》
No 12. 《Evolving the Hearthstone Meta》
No 13. 《Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning》
No 14. 《Video Crowd Counting via Dynamic Temporal Modeling》
No 15. 《Learning Markov models via low-rank optimization》
No 16. 《Mask Embedding in conditional GAN for Guided Synthesis of High Resolution Images》
No 17. 《Learning Landmarks from Unaligned Data using Image Translation》
No 18. 《Sparse Networks from Scratch: Faster Training without Losing Performance》
No 19. 《Curriculum Learning for Deep Generative Models with Clustering》
No 20. 《BAM! Born-Again Multi-Task Networks for Natural Language Understanding》
No 21. 《Guided Image Generation with Conditional Invertible Neural Networks》
No 22. 《M3D-GAN: Multi-Modal Multi-Domain Translation with Universal Attention》
No 23. 《Variational Autoencoders and Nonlinear ICA: A Unifying Framework》
No 24. 《PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows》
No 25. 《BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs》
No 26. 《Do Transformer Attention Heads Provide Transparency in Abstractive Summarization?》
No 27. 《Topic Modeling in Embedding Spaces》
No 28. 《A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks》
No 29. 《UnsuperPoint: End-to-end Unsupervised Interest Point Detector and Descriptor》
No 30. 《MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation》

发表评论

电子邮件地址不会被公开。 必填项已用*标注