| Pix2seq: A Language Modeling Framework for Object Detection | 0 | 0.34 | 2022 |
| Unsupervised Part Representation by Flow Capsules | 0 | 0.34 | 2021 |
| Teaching with Commentaries | 0 | 0.34 | 2021 |
| Deep learning for AI | 5 | 0.45 | 2021 |
| Teaching with Commentaries. | 0 | 0.34 | 2021 |
| CvxNet: Learnable Convex Decomposition | 7 | 0.42 | 2020 |
| Imputer: Sequence Modelling via Imputation and Dynamic Programming | 0 | 0.34 | 2020 |
| Big Self-Supervised Models are Strong Semi-Supervised Learners | 0 | 0.34 | 2020 |
| A Simple Framework for Contrastive Learning of Visual Representations | 2 | 0.36 | 2020 |
| Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions. | 0 | 0.34 | 2020 |
| The Next Generation of Neural Networks | 0 | 0.34 | 2020 |
| Analyzing and Improving Representations with the Soft Nearest Neighbor Loss. | 1 | 0.35 | 2019 |
| Similarity of Neural Network Representations Revisited. | 2 | 0.36 | 2019 |
| When Does Label Smoothing Help? | 7 | 0.40 | 2019 |
| Learning Sparse Networks Using Targeted Dropout. | 1 | 0.36 | 2019 |
| Cerberus: A Multi-headed Derenderer. | 0 | 0.34 | 2019 |
| Stacked Capsule Autoencoders. | 0 | 0.34 | 2019 |
| Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures | 0 | 0.34 | 2018 |
| Who Said What: Modeling Individual Labelers Improves Classification | 12 | 0.65 | 2018 |
| Large scale distributed neural network training through online distillation. | 0 | 0.34 | 2018 |
| Illustrative Language Understanding: Large-Scale Visual Grounding With Image Search | 0 | 0.34 | 2018 |
| Large scale distributed neural network training through online distillation. | 18 | 0.68 | 2018 |
| Matrix capsules with EM routing | 47 | 1.52 | 2018 |
| DARCCC: Detecting Adversaries by Reconstruction from Class Conditional Capsules. | 5 | 0.42 | 2018 |
| Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. | 95 | 3.02 | 2017 |
| Distilling a Neural Network Into a Soft Decision Tree. | 18 | 0.64 | 2017 |
| Regularizing Neural Networks by Penalizing Confident Output Distributions. | 42 | 1.24 | 2017 |
| Regularizing Neural Networks by Penalizing Confident Output Distributions. | 0 | 0.34 | 2017 |
| Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. | 0 | 0.34 | 2017 |
| Attend, Infer, Repeat: Fast Scene Understanding with Generative Models | 0 | 0.34 | 2016 |
| Layer Normalization. | 0 | 0.34 | 2016 |
| A Simple Way to Initialize Recurrent Networks of Rectified Linear Units. | 94 | 3.55 | 2015 |
| Distilling the Knowledge in a Neural Network. | 696 | 21.80 | 2015 |
| Guest Editorial: Deep Learning | 3 | 0.38 | 2015 |
| Application of Deep Belief Networks for Natural Language Understanding | 83 | 2.32 | 2014 |
| Grammar as a Foreign Language. | 237 | 10.73 | 2014 |
| Autoregressive product of multi-frame predictions can improve the accuracy of hybrid models. | 0 | 0.34 | 2014 |
| Dropout: a simple way to prevent neural networks from overfitting | 3420 | 130.13 | 2014 |
| Where do features come from? | 6 | 0.42 | 2014 |
| Tensor Analyzers. | 0 | 0.34 | 2013 |
| Modeling Documents with Deep Boltzmann Machines. | 64 | 3.62 | 2013 |
| Discovering Multiple Constraints that are Frequently Approximately Satisfied | 12 | 4.73 | 2013 |
| New types of deep neural network learning for speech recognition and related applications: an overview | 181 | 8.00 | 2013 |
| Modeling Natural Images Using Gated MRFs | 25 | 1.65 | 2013 |
| Improving deep neural networks for LVCSR using rectified linear units and dropout. | 83 | 5.62 | 2013 |
| Speech recognition with deep recurrent neural networks | 454 | 23.81 | 2013 |
| Efficient parametric projection pursuit density estimation | 1 | 1.32 | 2012 |
| Deep Lambertian Networks. | 1 | 0.35 | 2012 |
| Conditional Restricted Boltzmann Machines for Structured Output Prediction | 36 | 2.24 | 2012 |
| Visualizing non-metric similarities in multiple maps | 28 | 1.18 | 2012 |
