爱可可老师一周论文精选(2019.2.3)

No 1. 《One-Class Convolutional Neural Network》
No 2. 《The Evolved Transformer》
No 3. 《BioBERT: pre-trained biomedical language representation model for biomedical text mining》
No 4. 《Deep Learning on Small Datasets without Pre-Training using Cosine Loss》
No 5. 《A BERT Baseline for the Natural Questions》
No 6. 【综述:大脑误差反向传播理论】
No 7. 《Glyce: Glyph-vectors for Chinese Character Representations》
No 8. 《Hotels-50K: A Global Hotel Recognition Dataset》
No 9. 《Fixup Initialization: Residual Learning Without Normalization》
No 10. 《Self-Supervised Generalisation with Meta Auxiliary Learning》
No 11. 《MONet: Unsupervised Scene Decomposition and Representation》
No 12. 《Disentangling Disentanglement in Variational Auto-Encoders》
No 13. 《Design of Real-time Semantic Segmentation Decoder for Automated Driving》
No 14. 《Random Forest with Learned Representations for Semantic Segmentation》
No 15. 《In Defense of the Triplet Loss for Visual Recognition》
No 16. 《Joint shape learning and segmentation for medical images using a minimalistic deep network》
No 17. 《Theoretically Principled Trade-off between Robustness and Accuracy》
No 18. 《Spatial-Temporal Graph Convolutional Networks for Sign Language Recognition》
No 19. 《Hierarchical Attentional Hybrid Neural Networks for Document Classification》
No 20. 《Towards a Deeper Understanding of Adversarial Losses》
No 21. 《Chester: A Web Delivered Locally Computed Chest X-Ray Disease Prediction System》
No 22. 《Self-Supervised Deep Image Denoising》
No 23. 《What does the free energy principle tell us about the brain?》
No 24. 《Predicting Parkinson's Disease using Latent Information extracted from Deep Neural Networks》
No 25. 《Hierarchically Clustered Representation Learning》
No 26. 《Max-margin Class Imbalanced Learning with Gaussian Affinity》
No 27. 《Fast Markov Chain Monte Carlo Algorithms via Lie Groups》
No 28. 《Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge》
No 29. 《Reward Shaping via Meta-Learning》
No 30. 《Active Anomaly Detection via Ensembles: Insights, Algorithms, and Interpretability》

发表评论

电子邮件地址不会被公开。 必填项已用*标注