Neural Network Optimization

Deep Learning without Poor Local Minima NeurIPS 2016 Deeply-Recursive Convolutional Network for Image Super-Resolution CVPR 2016 DeepMath - Deep Sequence Models for Premise Selection NeurIPS 2016 Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin ICML 2016 Direct Feedback Alignment Provides Learning in Deep Neural Networks NeurIPS 2016 Disfluency Detection Using a Bidirectional LSTM Interspeech 2016 DrMAD: Distilling Reverse-Mode Automatic Differentiation for Optimizing Hyperparameters of Deep Neural Networks IJCAI 2016 End-to-End Training of Deep Visuomotor Policies JMLR 2016 Energetic Natural Gradient Descent ICML 2016 Expressive Speech Driven Talking Avatar Synthesis with DBLSTM Using Limited Amount of Emotional Bimodal Data Interspeech 2016 Fast ConvNets Using Group-Wise Brain Damage CVPR 2016 Frequency Estimation from Waveforms Using Multi-Layered Neural Networks Interspeech 2016 Full-Capacity Unitary Recurrent Neural Networks NeurIPS 2016 Generalization Properties and Implicit Regularization for Multiple Passes SGM ICML 2016 Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods NeurIPS 2016 GMM-Free Flat Start Sequence-Discriminative DNN Training Interspeech 2016 Gradual DropIn of Layers to Train Very Deep Neural Networks CVPR 2016 How Far Are We From Solving Pedestrian Detection? CVPR 2016 How to Center Deep Boltzmann Machines JMLR 2016 Hybrid Accelerated Optimization for Speech Recognition Interspeech 2016 Hyperparameter optimization with approximate gradient ICML 2016 Improved Neural Network Initialization by Grouping Context-Dependent Targets for Acoustic Modeling Interspeech 2016 Improved SVRG for Non-Strongly-Convex or Sum-of-Non-Convex Objectives ICML 2016 Interactive Attention for Neural Machine Translation COLING 2016 Learning Structured Sparsity in Deep Neural Networks NeurIPS 2016