【论文整理】Paper notes 2016-11

2016-11 (ICLR Edition)

• Image-to-Image Translation with Conditional Adversarial Networks [arXiv]
• Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer [OpenReview]
• Learning to reinforcement learn [arXiv]
• A Way out of the Odyssey: Analyzing and Combining Recent Insights for LSTMs [arXiv]
• Adversarial Training Methods for Semi-Supervised Text Classification [arXiv]
• Importance Sampling with Unequal Support [arXiv]
• Quasi-Recurrent Neural Networks [arXiv]
• Capacity and Learnability in Recurrent Neural Networks [OpenReview]
• Unrolled Generative Adversarial Networks [OpenReview]
• Deep Information Propagation [OpenReview]
• Structured Attention Networks [OpenReview]
• Incremental Sequence Learning [arXiv]
• Delving into Transferable Adversarial Examples and Black-box Attacks [arXiv] [code]
• b-GAN: Unified Framework of Generative Adversarial Networks [OpenReview]
• A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks [OpenReview]
• Categorical Reparameterization with Gumbel-Softmax [arXiv]
• Lip Reading Sentences in the Wild [arXiv]