Neural Network Optimization

Programming with a Differentiable Forth Interpreter ICML 2017 Pronunciation Learning with RNN-Transducers Interspeech 2017 Random Shifting for CNN: a Solution to Reduce Information Loss in Down-Sampling Layers IJCAI 2017 Recovery Guarantees for One-hidden-layer Neural Networks ICML 2017 Recurrent Neural Aligner: An Encoder-Decoder Neural Network Model for Sequence to Sequence Mapping Interspeech 2017 Relative Fisher Information and Natural Gradient for Learning Large Modular Models ICML 2017 Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice NeurIPS 2017 Robustness Over Time-Varying Channels in DNN-HMM ASR Based Human-Robot Interaction Interspeech 2017 Runtime Neural Pruning NeurIPS 2017 Self-Normalizing Neural Networks NeurIPS 2017 SGD Learns the Conjugate Kernel Class of the Network NeurIPS 2017 Sharp Minima Can Generalize For Deep Nets ICML 2017 Sharpness, Restart and Acceleration NeurIPS 2017 Sobolev Training for Neural Networks NeurIPS 2017 Social Signal Detection in Spontaneous Dialogue Using Bidirectional LSTM-CTC Interspeech 2017 Stochastic Gradient Descent as Approximate Bayesian Inference JMLR 2017 Stochastic Mirror Descent in Variationally Coherent Optimization Problems NeurIPS 2017 Structured-Based Curriculum Learning for End-to-End English-Japanese Speech Translation Interspeech 2017 Surprising properties of dropout in deep networks COLT 2017 TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning NeurIPS 2017 The Marginal Value of Adaptive Gradient Methods in Machine Learning NeurIPS 2017 The Reversible Residual Network: Backpropagation Without Storing Activations NeurIPS 2017 The Shattered Gradients Problem: If resnets are the answer, then what is the question? ICML 2017 To Improve the Robustness of LSTM-RNN Acoustic Models Using Higher-Order Feedback from Multiple Histories Interspeech 2017 Towards Generalization and Simplicity in Continuous Control NeurIPS 2017