Deep Learning

The Numerics of GANs NeurIPS 2017 Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank ICML 2017 The Predictron: End-To-End Learning and Planning ICML 2017 The Reversible Residual Network: Backpropagation Without Storing Activations NeurIPS 2017 The Role of Linguistic and Prosodic Cues on the Prediction of Self-Reported Satisfaction in Contact Centre Phone Calls Interspeech 2017 The Shattered Gradients Problem: If resnets are the answer, then what is the question? ICML 2017 The Statistical Recurrent Unit ICML 2017 The STC Keyword Search System for OpenKWS 2016 Evaluation Interspeech 2017 The strange geometry of skip-gram with negative sampling EMNLP 2017 Thinking Fast and Slow with Deep Learning and Tree Search NeurIPS 2017 Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos CVPR 2017 THU_NGN at IJCNLP-2017 Task 2: Dimensional Sentiment Analysis for Chinese Phrases with Deep LSTM IJCNLP 2017 Tied Hidden Factors in Neural Networks for End-to-End Speaker Recognition Interspeech 2017 Tied Variational Autoencoder Backends for i-Vector Speaker Recognition Interspeech 2017 Tight Integration of Spatial and Spectral Features for BSS with Deep Clustering Embeddings Interspeech 2017 To Improve the Robustness of LSTM-RNN Acoustic Models Using Higher-Order Feedback from Multiple Histories Interspeech 2017 Top-Down Visual Saliency Guided by Captions CVPR 2017 Topically Driven Neural Language Model ACL 2017 To Plan or not to Plan? Discourse Planning in Slot-Value Informed Sequence to Sequence Models for Language Generation Interspeech 2017 Toward Controlled Generation of Text ICML 2017 Toward Multimodal Image-to-Image Translation NeurIPS 2017 Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks NeurIPS 2017 Towards Accurate Binary Convolutional Neural Network NeurIPS 2017 Towards Bidirectional Hierarchical Representations for Attention-based Neural Machine Translation EMNLP 2017 Towards Compact and Fast Neural Machine Translation Using a Combined Method EMNLP 2017