Deep Learning

On Random Deep Weight-Tied Autoencoders: Exact Asymptotic Analysis, Phase Transitions, and Implications to Training ICLR 2019 On Reinforcement Learning for Full-Length Game of StarCraft AAAI 2019 On Relating Explanations and Adversarial Examples NeurIPS 2019 On Retrospecting Human Dynamics with Attention IJCAI 2019 On Self Modulation for Generative Adversarial Networks ICLR 2019 On Single Source Robustness in Deep Fusion Models NeurIPS 2019 On Stabilizing Generative Adversarial Training With Noise CVPR 2019 On The Classification-Distortion-Perception Tradeoff NeurIPS 2019 On the Connection Between Learning Two-Layer Neural Networks and Tensor Decomposition AISTATS 2019 On the Continuity of Rotation Representations in Neural Networks CVPR 2019 On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization ICLR 2019 On the Convergence Rate of Training Recurrent Neural Networks NeurIPS 2019 On the Downstream Performance of Compressed Word Embeddings NeurIPS 2019 On the Dynamics of Gradient Descent for Autoencoders AISTATS 2019 On the Effectiveness of the Pooling Methods for Biomedical Relation Extraction with Deep Learning EMNLP 2019 On the equivalence between graph isomorphism testing and function approximation with GNNs NeurIPS 2019 On the Expressive Power of Deep Polynomial Neural Networks NeurIPS 2019 On the Impact of the Activation function on Deep Neural Networks Training ICML 2019 On the Importance of the Kullback-Leibler Divergence Term in Variational Autoencoders for Text Generation EMNLP 2019 On the Importance of Word Boundaries in Character-level Neural Machine Translation EMNLP 2019 On the Intrinsic Dimensionality of Image Representations CVPR 2019 On the Merits of Joint Space and Orientation Representations in Learning the Forward Kinematics in SE(3) RSS 2019 On the Power and Limitations of Random Features for Understanding Neural Networks NeurIPS 2019 On The Power of Curriculum Learning in Training Deep Networks ICML 2019 On the Realization of Compositionality in Neural Networks ACL 2019