Table of Contents

• Online Bayesian Transfer Learning for Sequential Data ModelingPriyank Jaini, Zhitang Chen, Pablo Carbajal, Edith Law, Laura Middleton, Kayla Regan, Mike Schaekermann, George Trimponias, James Tung, Pascal Poupart. [doi]
• Combining policy gradient and Q-learningBrendan O'Donoghue, Rémi Munos, Koray Kavukcuoglu, Volodymyr Mnih. [doi]
• Towards the Limit of Network QuantizationYoojin Choi, Mostafa El-Khamy, Jungwon Lee. [doi]
• Tree-structured decoding with doubly-recurrent neural networksDavid Alvarez-Melis, Tommi S. Jaakkola. [doi]
• Unsupervised Cross-Domain Image GenerationYaniv Taigman, Adam Polyak, Lior Wolf. [doi]
• Learning to Perform Physics Experiments via Deep Reinforcement LearningMisha Denil, Pulkit Agrawal, Tejas D. Kulkarni, Tom Erez, Peter Battaglia, Nando de Freitas. [doi]
• Pruning Filters for Efficient ConvNetsHao Li 0022, Asim Kadav, Igor Durdanovic, Hanan Samet, Hans Peter Graf. [doi]
• SampleRNN: An Unconditional End-to-End Neural Audio Generation ModelSoroush Mehri, Kundan Kumar, Ishaan Gulrajani, Rithesh Kumar, Shubham Jain, Jose Sotelo, Aaron C. Courville, Yoshua Bengio. [doi]
• Sample Efficient Actor-Critic with Experience ReplayZiyu Wang 0001, Victor Bapst, Nicolas Heess, Volodymyr Mnih, Rémi Munos, Koray Kavukcuoglu, Nando de Freitas. [doi]
• beta-VAE: Learning Basic Visual Concepts with a Constrained Variational FrameworkIrina Higgins, Loïc Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, Alexander Lerchner. [doi]
• Efficient Representation of Low-Dimensional Manifolds using Deep NetworksRonen Basri, David W. Jacobs. [doi]
• Machine Comprehension Using Match-LSTM and Answer PointerShuohang Wang, Jing Jiang 0001. [doi]
• Towards a Neural StatisticianHarrison Edwards, Amos J. Storkey. [doi]
• Multi-Agent Cooperation and the Emergence of (Natural) LanguageAngeliki Lazaridou, Alexander Peysakhovich, Marco Baroni. [doi]
• Calibrating Energy-based Generative Adversarial NetworksZihang Dai, Amjad Almahairi, Philip Bachman, Eduard H. Hovy, Aaron C. Courville. [doi]
• Batch Policy Gradient Methods for Improving Neural Conversation ModelsKirthevasan Kandasamy, Yoram Bachrach, Ryota Tomioka, Daniel Tarlow, David Carter. [doi]
• Learning to Navigate in Complex EnvironmentsPiotr Mirowski, Razvan Pascanu, Fabio Viola, Hubert Soyer, Andy Ballard, Andrea Banino, Misha Denil, Ross Goroshin, Laurent Sifre, Koray Kavukcuoglu, Dharshan Kumaran, Raia Hadsell. [doi]
• Loss-aware Binarization of Deep NetworksLu Hou, Quanming Yao, James T. Kwok. [doi]
• Temporal Ensembling for Semi-Supervised LearningSamuli Laine, Timo Aila. [doi]
• Snapshot Ensembles: Train 1, Get M for FreeGao Huang, Yixuan Li, Geoff Pleiss, Zhuang Liu 0003, John E. Hopcroft, Kilian Q. Weinberger. [doi]
• Autoencoding Variational Inference For Topic ModelsAkash Srivastava, Charles A. Sutton. [doi]
• Semi-supervised Knowledge Transfer for Deep Learning from Private Training DataNicolas Papernot, Martín Abadi, Úlfar Erlingsson, Ian J. Goodfellow, Kunal Talwar. [doi]
• Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention TransferSergey Zagoruyko, Nikos Komodakis. [doi]
• DeepDSL: A Compilation-based Domain-Specific Language for Deep LearningTian Zhao, Xiaobing Huang, Yu Cao. [doi]
• Sparsely-Connected Neural Networks: Towards Efficient VLSI Implementation of Deep Neural NetworksArash Ardakani, Carlo Condo, Warren J. Gross. [doi]
• Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPUMohammad Babaeizadeh, Iuri Frosio, Stephen Tyree, Jason Clemons, Jan Kautz. [doi]
• An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population InfomaxWentao Huang, Kechen Zhang. [doi]
• Nonparametric Neural NetworksGeorge Philipp, Jaime G. Carbonell. [doi]
• Inductive Bias of Deep Convolutional Networks through Pooling GeometryNadav Cohen, Amnon Shashua. [doi]
• Amortised MAP Inference for Image Super-resolutionCasper Kaae Sønderby, Jose Caballero, Lucas Theis, Wenzhe Shi, Ferenc Huszár. [doi]
• Tracking the World State with Recurrent Entity NetworksMikael Henaff, Jason Weston, Arthur Szlam, Antoine Bordes, Yann LeCun. [doi]
• Neural Architecture Search with Reinforcement LearningBarret Zoph, Quoc V. Le. [doi]
• Towards Deep Interpretability (MUS-ROVER II): Learning Hierarchical Representations of Tonal MusicHaizi Yu, Lav R. Varshney. [doi]
• Deep Predictive Coding Networks for Video Prediction and Unsupervised LearningWilliam Lotter, Gabriel Kreiman, David Cox. [doi]
• Deep Learning with Dynamic Computation GraphsMoshe Looks, Marcello Herreshoff, DeLesley Hutchins, Peter Norvig. [doi]
• Towards Principled Methods for Training Generative Adversarial NetworksMartín Arjovsky, Léon Bottou. [doi]
• SGDR: Stochastic Gradient Descent with Warm RestartsIlya Loshchilov, Frank Hutter. [doi]
• Pointer Sentinel Mixture ModelsStephen Merity, Caiming Xiong, James Bradbury 0002, Richard Socher. [doi]
• Generalizing Skills with Semi-Supervised Reinforcement LearningChelsea Finn, Tianhe Yu, Justin Fu, Pieter Abbeel, Sergey Levine. [doi]
• Multi-view Recurrent Neural Acoustic Word EmbeddingsWanjia He, Weiran Wang, Karen Livescu. [doi]
• Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts LayerNoam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc V. Le, Geoffrey E. Hinton, Jeff Dean. [doi]
• Learning Graphical State TransitionsDaniel D. Johnson. [doi]
• Faster CNNs with Direct Sparse Convolutions and Guided PruningJongSoo Park, Sheng R. Li, Wei Wen, Ping Tak Peter Tang, Hai Li 0001, Yiran Chen, Pradeep Dubey. [doi]
• Recurrent Hidden Semi-Markov ModelHanjun Dai, Bo Dai, Yan-Ming Zhang, Shuang Li 0002, Le Song. [doi]
• Unrolled Generative Adversarial NetworksLuke Metz, Ben Poole, David Pfau, Jascha Sohl-Dickstein. [doi]
• Revisiting Classifier Two-Sample TestsDavid Lopez-Paz, Maxime Oquab. [doi]
• Learning Visual Servoing with Deep Features and Fitted Q-IterationAlex X. Lee, Sergey Levine, Pieter Abbeel. [doi]
• A recurrent neural network without chaosThomas Laurent 0001, James von Brecht. [doi]
• Generative Models and Model Criticism via Optimized Maximum Mean DiscrepancyDougal J. Sutherland, Hsiao-Yu Tung, Heiko Strathmann, Soumyajit De, Aaditya Ramdas, Alexander J. Smola, Arthur Gretton. [doi]
• Adversarial Machine Learning at ScaleAlexey Kurakin, Ian J. Goodfellow, Samy Bengio. [doi]
• On Detecting Adversarial PerturbationsJan Hendrik Metzen, Tim Genewein, Volker Fischer, Bastian Bischoff. [doi]
• A Compositional Object-Based Approach to Learning Physical DynamicsMichael Chang 0003, Tomer Ullman, Antonio Torralba 0001, Joshua B. Tenenbaum. [doi]
• Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domainJanarthanan Rajendran, Aravind S. Lakshminarayanan, Mitesh M. Khapra, P. Prasanna, Balaraman Ravindran. [doi]
• Emergence of foveal image sampling from learning to attend in visual scenesBrian Cheung, Eric Weiss, Bruno A. Olshausen. [doi]
• Improving Policy Gradient by Exploring Under-appreciated RewardsOfir Nachum, Mohammad Norouzi 0002, Dale Schuurmans. [doi]
• Optimization as a Model for Few-Shot LearningSachin Ravi, Hugo Larochelle. [doi]
• Designing Neural Network Architectures using Reinforcement LearningBowen Baker, Otkrist Gupta, Nikhil Naik, Ramesh Raskar. [doi]
• Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement LearningSahil Sharma, Aravind S. Lakshminarayanan, Balaraman Ravindran. [doi]
• Incremental Network Quantization: Towards Lossless CNNs with Low-precision WeightsAojun Zhou, Anbang Yao, Yiwen Guo, Lin Xu, Yurong Chen. [doi]
• Predicting Medications from Diagnostic Codes with Recurrent Neural NetworksJacek M. Bajor, Thomas A. Lasko. [doi]
• Training deep neural-networks using a noise adaptation layerJacob Goldberger, Ehud Ben-Reuven. [doi]
• Categorical Reparameterization with Gumbel-SoftmaxEric Jang, Shixiang Gu, Ben Poole. [doi]
• Trusting SVM for Piecewise Linear CNNsLeonard Berrada, Andrew Zisserman, M. Pawan Kumar. [doi]
• Entropy-SGD: Biasing Gradient Descent Into Wide ValleysPratik Chaudhari, Anna Choromanska, Stefano Soatto, Yann LeCun, Carlo Baldassi, Christian Borgs, Jennifer T. Chayes, Levent Sagun, Riccardo Zecchina. [doi]
• Variable Computation in Recurrent Neural NetworksYacine Jernite, Edouard Grave, Armand Joulin, Tomas Mikolov. [doi]
• Transfer Learning for Sequence Tagging with Hierarchical Recurrent NetworksZhilin Yang, Ruslan Salakhutdinov, William W. Cohen. [doi]
• Learning Curve Prediction with Bayesian Neural NetworksAaron Klein, Stefan Falkner, Jost Tobias Springenberg, Frank Hutter. [doi]
• The Concrete Distribution: A Continuous Relaxation of Discrete Random VariablesChris J. Maddison, Andriy Mnih, Yee Whye Teh. [doi]
• Hyperband: Bandit-Based Configuration Evaluation for Hyperparameter OptimizationLisha Li, Kevin G. Jamieson, Giulia DeSalvo, Afshin Rostamizadeh, Ameet Talwalkar. [doi]
• Delving into Transferable Adversarial Examples and Black-box AttacksYanpei Liu, Xinyun Chen, Chang Liu, Dawn Song. [doi]
• Improving Neural Language Models with a Continuous CacheEdouard Grave, Armand Joulin, Nicolas Usunier. [doi]
• Adversarially Learned InferenceVincent Dumoulin, Ishmael Belghazi, Ben Poole, Alex Lamb, Martín Arjovsky, Olivier Mastropietro, Aaron C. Courville. [doi]
• Lossy Image Compression with Compressive AutoencodersLucas Theis, Wenzhe Shi, Andrew Cunningham, Ferenc Huszár. [doi]
• Understanding deep learning requires rethinking generalizationChiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, Oriol Vinyals. [doi]
• The Neural Noisy ChannelLei Yu, Phil Blunsom, Chris Dyer, Edward Grefenstette, Tomás Kociský. [doi]
• Regularizing CNNs with Locally Constrained DecorrelationsPau Rodríguez, Jordi Gonzàlez 0001, Guillem Cucurull, Josep M. Gonfaus, F. Xavier Roca. [doi]
• Lie-Access Neural Turing MachinesGreg Yang, Alexander M. Rush. [doi]
• Support Regularized Sparse Coding and Its Fast EncoderYingzhen Yang, Jiahui Yu, Pushmeet Kohli, Jianchao Yang, Thomas S. Huang. [doi]
• LR-GAN: Layered Recursive Generative Adversarial Networks for Image GenerationJianwei Yang, Anitha Kannan, Dhruv Batra, Devi Parikh. [doi]
• Maximum Entropy Flow NetworksGabriel Loaiza-Ganem, Yuanjun Gao, John P. Cunningham. [doi]
• Learning to Generate Samples from Noise through Infusion TrainingFlorian Bordes, Sina Honari, Pascal Vincent. [doi]
• Recurrent Environment SimulatorsSilvia Chiappa, Sébastien Racanière, Daan Wierstra, Shakir Mohamed. [doi]
• Deep Multi-task Representation Learning: A Tensor Factorisation ApproachYongxin Yang, Timothy M. Hospedales. [doi]
• Capacity and Trainability in Recurrent Neural NetworksJasmine Collins, Jascha Sohl-Dickstein, David Sussillo. [doi]
• Structured Attention NetworksYoon Kim, Carl Denton, Luong Hoang, Alexander M. Rush. [doi]
• Recurrent Batch NormalizationTim Cooijmans, Nicolas Ballas, César Laurent, Çaglar Gülçehre, Aaron C. Courville. [doi]
• Reasoning with Memory Augmented Neural Networks for Language ComprehensionTsendsuren Munkhdalai, Hong Yu. [doi]
• Soft Weight-Sharing for Neural Network CompressionKaren Ullrich, Edward Meeds, Max Welling. [doi]
• Learning to Compose Words into Sentences with Reinforcement LearningDani Yogatama, Phil Blunsom, Chris Dyer, Edward Grefenstette, Wang Ling. [doi]
• On Large-Batch Training for Deep Learning: Generalization Gap and Sharp MinimaNitish Shirish Keskar, Dheevatsa Mudigere, Jorge Nocedal, Mikhail Smelyanskiy, Ping Tak Peter Tang. [doi]
• Quasi-Recurrent Neural NetworksJames Bradbury 0002, Stephen Merity, Caiming Xiong, Richard Socher. [doi]
• Do Deep Convolutional Nets Really Need to be Deep and Convolutional?Gregor Urban, Krzysztof J. Geras, Samira Ebrahimi Kahou, Özlem Aslan, Shengjie Wang, Abdelrahman Mohamed, Matthai Philipose, Matthew Richardson, Rich Caruana. [doi]
• HyperNetworksDavid Ha, Andrew M. Dai, Quoc V. Le. [doi]
• A Learned Representation For Artistic StyleVincent Dumoulin, Jonathon Shlens, Manjunath Kudlur. [doi]
• Distributed Second-Order Optimization using Kronecker-Factored ApproximationsJimmy Ba, Roger Grosse, James Martens. [doi]
• Understanding Trainable Sparse Coding with Matrix FactorizationThomas Moreau, Joan Bruna. [doi]
• Automatic Rule Extraction from Long Short Term Memory NetworksW. James Murdoch, Arthur Szlam. [doi]
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural NetworksDan Hendrycks, Kevin Gimpel. [doi]
• Training Agent for First-Person Shooter Game with Actor-Critic Curriculum LearningYuxin Wu, Yuandong Tian. [doi]
• DeepCoder: Learning to Write ProgramsMatej Balog, Alexander L. Gaunt, Marc Brockschmidt, Sebastian Nowozin, Daniel Tarlow. [doi]
• Frustratingly Short Attention Spans in Neural Language ModelingMichal Daniluk, Tim Rocktäschel, Johannes Welbl, Sebastian Riedel 0001. [doi]
• Normalizing the Normalizers: Comparing and Extending Network Normalization SchemesMengye Ren, Renjie Liao, Raquel Urtasun, Fabian H. Sinz, Richard S. Zemel. [doi]
• Learning to OptimizeKe Li, Jitendra Malik. [doi]
• Dynamic Coattention Networks For Question AnsweringCaiming Xiong, Victor Zhong, Richard Socher. [doi]
• Learning Invariant Representations Of Planar CurvesGautam Pai, Aaron Wetzler, Ron Kimmel. [doi]
• Deep Probabilistic ProgrammingDustin Tran, Matthew D. Hoffman, Rif A. Saurous, Eugene Brevdo, Kevin Murphy 0002, David M. Blei. [doi]
• Visualizing Deep Neural Network Decisions: Prediction Difference AnalysisLuisa M. Zintgraf, Taco S. Cohen, Tameem Adel, Max Welling. [doi]
• Learning End-to-End Goal-Oriented DialogAntoine Bordes, Y.-Lan Boureau, Jason Weston. [doi]
• Neural Photo Editing with Introspective Adversarial NetworksAndrew Brock, Theodore Lim, James M. Ritchie, Nick Weston. [doi]
• Improving Generative Adversarial Networks with Denoising Feature MatchingDavid Warde-Farley, Yoshua Bengio. [doi]
• PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other ModificationsTim Salimans, Andrej Karpathy, Xi Chen 0022, Diederik P. Kingma. [doi]
• HolStep: A Machine Learning Dataset for Higher-order Logic Theorem ProvingCezary Kaliszyk, François Chollet, Christian Szegedy. [doi]
• Variational Lossy AutoencoderXi Chen 0022, Diederik P. Kingma, Tim Salimans, Yan Duan, Prafulla Dhariwal, John Schulman, Ilya Sutskever, Pieter Abbeel. [doi]
• Deep Variational Information BottleneckAlexander A. Alemi, Ian Fischer, Joshua V. Dillon, Kevin Murphy 0002. [doi]
• Program Synthesis for Character Level Language ModelingPavol Bielik, Veselin Raychev, Martin T. Vechev. [doi]
• Tying Word Vectors and Word Classifiers: A Loss Framework for Language ModelingHakan Inan, Khashayar Khosravi, Richard Socher. [doi]
• Adversarial Feature LearningJeff Donahue, Philipp Krähenbühl, Trevor Darrell. [doi]
• Diet Networks: Thin Parameters for Fat GenomicsAdriana Romero, Pierre Luc Carrier, Akram Erraqabi, Tristan Sylvain, Alex Auvolat, Etienne Dejoie, Marc-André Legault, Marie-Pierre Dubé, Julie G. Hussin, Yoshua Bengio. [doi]
• Learning Invariant Feature Spaces to Transfer Skills with Reinforcement LearningAbhishek Gupta 0004, Coline Devin, Yuxuan Liu, Pieter Abbeel, Sergey Levine. [doi]
• Deep Biaffine Attention for Neural Dependency ParsingTimothy Dozat, Christopher D. Manning. [doi]
• Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural NetworksStefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft. [doi]
• Learning to Act by Predicting the FutureAlexey Dosovitskiy, Vladlen Koltun. [doi]
• Offline bilingual word vectors, orthogonal transformations and the inverted softmaxSamuel L. Smith, David H. P. Turban, Steven Hamblin, Nils Y. Hammerla. [doi]
• Semi-Supervised Classification with Graph Convolutional NetworksThomas N. Kipf, Max Welling. [doi]
• PixelVAE: A Latent Variable Model for Natural ImagesIshaan Gulrajani, Kundan Kumar, Faruk Ahmed, Adrien Ali Taïga, Francesco Visin, David Vázquez, Aaron C. Courville. [doi]
• Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality TighteningFrank S. He, Yang Liu 0097, Alexander G. Schwing, Jian Peng 0001. [doi]
• What does it take to generate natural textures?Ivan Ustyuzhaninov, Wieland Brendel, Leon A. Gatys, Matthias Bethge. [doi]
• Sigma Delta Quantized NetworksPeter O'Connor, Max Welling. [doi]
• Words or Characters? Fine-grained Gating for Reading ComprehensionZhilin Yang, Bhuwan Dhingra, Ye Yuan, Junjie Hu, William W. Cohen, Ruslan Salakhutdinov. [doi]
• Pruning Convolutional Neural Networks for Resource Efficient InferencePavlo Molchanov, Stephen Tyree, Tero Karras, Timo Aila, Jan Kautz. [doi]
• Transfer of View-manifold Learning to Similarity Perception of Novel ObjectsXingyu Lin, Hao Wang, Zhihao Li, Yimeng Zhang, Alan L. Yuille, Tai Sing Lee. [doi]
• Bidirectional Attention Flow for Machine ComprehensionMin Joon Seo, Aniruddha Kembhavi, Ali Farhadi, Hannaneh Hajishirzi. [doi]
• Decomposing Motion and Content for Natural Video Sequence PredictionRuben Villegas, Jimei Yang, Seunghoon Hong, Xunyu Lin, Honglak Lee. [doi]
• Episodic Exploration for Deep Deterministic Policies for StarCraft MicromanagementNicolas Usunier, Gabriel Synnaeve, Zeming Lin, Soumith Chintala. [doi]
• Learning a Natural Language Interface with Neural ProgrammerArvind Neelakantan, Quoc V. Le, Martín Abadi, Andrew McCallum, Dario Amodei. [doi]
• Reinforcement Learning with Unsupervised Auxiliary TasksMax Jaderberg, Volodymyr Mnih, Wojciech Marian Czarnecki, Tom Schaul, Joel Z. Leibo, David Silver, Koray Kavukcuoglu. [doi]
• Training Compressed Fully-Connected Networks with a Density-Diversity PenaltyShengjie Wang, Haoran Cai, Jeff A. Bilmes, William S. Noble. [doi]
• Filter shaping for Convolutional Neural NetworksXingyi Li, Fuxin Li, Xiaoli Z. Fern, Raviv Raich. [doi]
• Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy CriticShixiang Gu, Timothy P. Lillicrap, Zoubin Ghahramani, Richard E. Turner, Sergey Levine. [doi]
• Adversarial Training Methods for Semi-Supervised Text ClassificationTakeru Miyato, Andrew M. Dai, Ian J. Goodfellow. [doi]
• Metacontrol for Adaptive Imagination-Based OptimizationJessica B. Hamrick, Andrew J. Ballard, Razvan Pascanu, Oriol Vinyals, Nicolas Heess, Peter W. Battaglia. [doi]
• A Compare-Aggregate Model for Matching Text SequencesShuohang Wang, Jing Jiang 0001. [doi]
• Exploring Sparsity in Recurrent Neural NetworksSharan Narang, Greg Diamos, Shubho Sengupta, Erich Elsen. [doi]
• Trained Ternary QuantizationChenzhuo Zhu, Song Han, Huizi Mao, William J. Dally. [doi]
• Dropout with Expectation-linear RegularizationXuezhe Ma, Yingkai Gao, Zhiting Hu, Yaoliang Yu, Yuntian Deng, Eduard H. Hovy. [doi]
• Generative Multi-Adversarial NetworksIshan P. Durugkar, Ian Gemp, Sridhar Mahadevan. [doi]
• A Simple but Tough-to-Beat Baseline for Sentence EmbeddingsSanjeev Arora, Yingyu Liang, Tengyu Ma. [doi]
• End-to-end Optimized Image CompressionJohannes Ballé, Valero Laparra, Eero P. Simoncelli. [doi]
• Neural Program LatticesChengtao Li, Daniel Tarlow, Alexander L. Gaunt, Marc Brockschmidt, Nate Kushman. [doi]
• Tighter bounds lead to improved classifiersNicolas Le Roux. [doi]
• Highway and Residual Networks learn Unrolled Iterative EstimationKlaus Greff, Rupesh Kumar Srivastava, Jürgen Schmidhuber. [doi]
• Learning Features of Music From ScratchJohn Thickstun, Zaïd Harchaoui, Sham Kakade. [doi]
• Stochastic Neural Networks for Hierarchical Reinforcement LearningCarlos Florensa, Yan Duan, Pieter Abbeel. [doi]
• Multilayer Recurrent Network Models of Primate Retinal Ganglion Cell ResponsesEleanor Batty, Josh Merel, Nora Brackbill, Alexander Heitman, Alexander Sher, Alan M. Litke, E. J. Chichilnisky, Liam Paninski. [doi]
• Energy-based Generative Adversarial NetworksJunbo Jake Zhao, Michaël Mathieu, Yann LeCun. [doi]
• Latent Sequence DecompositionsWilliam Chan, Yu Zhang, Quoc V. Le, Navdeep Jaitly. [doi]
• Steerable CNNsTaco S. Cohen, Max Welling. [doi]
• Discrete Variational AutoencodersJason Tyler Rolfe. [doi]
• EPOpt: Learning Robust Neural Network Policies Using Model EnsemblesAravind Rajeswaran, Sarvjeet Ghotra, Balaraman Ravindran, Sergey Levine. [doi]
• Topology and Geometry of Half-Rectified Network OptimizationC. Daniel Freeman, Joan Bruna. [doi]
• A Structured Self-Attentive Sentence EmbeddingZhouhan Lin, Minwei Feng, Cícero Nogueira dos Santos, Mo Yu, Bing Xiang, Bowen Zhou, Yoshua Bengio. [doi]
• Stick-Breaking Variational AutoencodersEric T. Nalisnick, Padhraic Smyth. [doi]
• Efficient Vector Representation for Documents through CorruptionMinmin Chen. [doi]
• TopicRNN: A Recurrent Neural Network with Long-Range Semantic DependencyAdji B. Dieng, Chong Wang 0002, Jianfeng Gao, John W. Paisley. [doi]
• Hadamard Product for Low-rank Bilinear PoolingJin-Hwa Kim, Kyoung-woon On, Woosang Lim, Jeonghee Kim, Jung-Woo Ha, Byoung-Tak Zhang. [doi]
• Data Noising as Smoothing in Neural Network Language ModelsZiang Xie, Sida I. Wang, Jiwei Li, Daniel Lévy, Aiming Nie, Dan Jurafsky, Andrew Y. Ng. [doi]
• Deep Information PropagationSamuel S. Schoenholz, Justin Gilmer, Surya Ganguli, Jascha Sohl-Dickstein. [doi]
• Identity Matters in Deep LearningMoritz Hardt, Tengyu Ma. [doi]
• Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw DataMaximilian Karl, Maximilian Sölch, Justin Bayer, Patrick van der Smagt. [doi]
• Incorporating long-range consistency in CNN-based texture generationGuillaume Berger, Roland Memisevic. [doi]
• Central Moment Discrepancy (CMD) for Domain-Invariant Representation LearningWerner Zellinger, Thomas Grubinger, Edwin Lughofer, Thomas Natschläger, Susanne Saminger-Platz. [doi]
• On the Quantitative Analysis of Decoder-Based Generative ModelsYuhuai Wu, Yuri Burda, Ruslan Salakhutdinov, Roger Grosse. [doi]
• Learning Recurrent Representations for Hierarchical Behavior ModelingEyrun Eyjolfsdottir, Kristin Branson, Yisong Yue, Pietro Perona. [doi]
• Learning to Query, Reason, and Answer Questions On Ambiguous TextsXiaoxiao Guo, Tim Klinger, Clemens Rosenbaum, Joseph P. Bigus, Murray Campbell, Ban Kawas, Kartik Talamadupula, Gerry Tesauro, Satinder Singh. [doi]
• Paleo: A Performance Model for Deep Neural NetworksHang Qi, Evan R. Sparks, Ameet Talwalkar. [doi]
• Dialogue Learning With Human-in-the-LoopJiwei Li, Alexander H. Miller, Sumit Chopra, Marc'Aurelio Ranzato, Jason Weston. [doi]
• Mode Regularized Generative Adversarial NetworksTong Che, Yanran Li, Athul Paul Jacob, Yoshua Bengio, Wenjie Li. [doi]
• Learning through Dialogue Interactions by Asking QuestionsJiwei Li, Alexander H. Miller, Sumit Chopra, Marc'Aurelio Ranzato, Jason Weston. [doi]
• Density estimation using Real NVPLaurent Dinh, Jascha Sohl-Dickstein, Samy Bengio. [doi]
• Making Neural Programming Architectures Generalize via RecursionJonathon Cai, Richard Shin, Dawn Song. [doi]
• Recurrent Mixture Density Network for Spatiotemporal Visual AttentionLoris Bazzani, Hugo Larochelle, Lorenzo Torresani. [doi]
• Geometry of PolysemyJiaqi Mu, Suma Bhat, Pramod Viswanath. [doi]
• Learning to superoptimize programsRudy Bunel, Alban Desmaison, M. Pawan Kumar, Philip H. S. Torr, Pushmeet Kohli. [doi]
• Introspection: Accelerating Neural Network Training By Learning Weight EvolutionAbhishek Sinha, Aahitagni Mukherjee, Mausoom Sarkar, Balaji Krishnamurthy. [doi]
• Optimal Binary Autoencoding with Pairwise CorrelationsAkshay Balsubramani. [doi]
• Neuro-Symbolic Program SynthesisEmilio Parisotto, Abdel-rahman Mohamed, Rishabh Singh, Lihong Li 0001, Dengyong Zhou, Pushmeet Kohli. [doi]
• Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction TasksYossi Adi, Einat Kermany, Yonatan Belinkov, Ofer Lavi, Yoav Goldberg. [doi]
• Query-Reduction Networks for Question AnsweringMin Joon Seo, Sewon Min, Ali Farhadi, Hannaneh Hajishirzi. [doi]
• Zoneout: Regularizing RNNs by Randomly Preserving Hidden ActivationsDavid Krueger, Tegan Maharaj, János Kramár, Mohammad Pezeshki, Nicolas Ballas, Nan Rosemary Ke, Anirudh Goyal, Yoshua Bengio, Aaron C. Courville, Christopher J. Pal. [doi]
• Third Person Imitation LearningBradly C. Stadie, Pieter Abbeel, Ilya Sutskever. [doi]
• Variational Recurrent Adversarial Deep Domain AdaptationSanjay Purushotham, Wilka Carvalho, Tanachat Nilanon, Yan Liu 0002. [doi]
• DSD: Dense-Sparse-Dense Training for Deep Neural NetworksSong Han, Jeff Pool, Sharan Narang, Huizi Mao, Enhao Gong, Shijian Tang, Erich Elsen, Peter Vajda, Manohar Paluri, John Tran, Bryan Catanzaro, William J. Dally. [doi]
• Learning to Remember Rare EventsLukasz Kaiser, Ofir Nachum, Aurko Roy, Samy Bengio. [doi]
• Why Deep Neural Networks for Function Approximation?Shiyu Liang, R. Srikant. [doi]
• Mollifying NetworksÇaglar Gülçehre, Marcin Moczulski, Francesco Visin, Yoshua Bengio. [doi]
• Hierarchical Multiscale Recurrent Neural NetworksJunyoung Chung, Sungjin Ahn, Yoshua Bengio. [doi]
• An Actor-Critic Algorithm for Sequence PredictionDzmitry Bahdanau, Philemon Brakel, Kelvin Xu, Anirudh Goyal, Ryan Lowe, Joelle Pineau, Aaron C. Courville, Yoshua Bengio. [doi]
• FractalNet: Ultra-Deep Neural Networks without ResidualsGustav Larsson, Michael Maire, Gregory Shakhnarovich. [doi]