| 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 |
| 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 |
| 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 |
| 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 |
| Illustrative Language Understanding: Large-Scale Visual Grounding With Image Search | 0 | 0.34 | 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| Two Distributed-State Models For Generating High-Dimensional Time Series | 42 | 1.86 | 2011 |
| Transforming auto-encoders | 74 | 7.46 | 2011 |
| Modeling the joint density of two images under a variety of transformations | 17 | 1.53 | 2011 |
| Deep belief nets for natural language call-routing | 29 | 1.08 | 2011 |
| A better way to learn features: technical perspective | 5 | 0.41 | 2011 |
| Comparing classification methods for longitudinal fMRI studies. | 12 | 0.74 | 2010 |
| Gated Softmax Classification. | 21 | 0.98 | 2010 |
| Phone Recognition Using Restricted Boltzmann Machines | 11 | 6.64 | 2010 |
| Learning to detect roads in high-resolution aerial images | 33 | 3.15 | 2010 |
| Rectified Linear Units Improve Restricted Boltzmann Machines | 1300 | 95.70 | 2010 |
| Learning to combine foveal glimpses with a third-order Boltzmann machine. | 93 | 5.69 | 2010 |
| Deep belief networks | 41 | 1.48 | 2009 |
| Learning Generative Texture Models with extended Fields-of-Experts | 132 | 7.91 | 2009 |
| Deep Boltzmann Machines | 0 | 0.34 | 2009 |
| Semantic hashing | 248 | 17.09 | 2009 |
| Replicated Softmax: an Undirected Topic Model. | 0 | 0.34 | 2009 |
| Zero-shot Learning with Semantic Output Codes. | 228 | 7.93 | 2009 |
| Products of Hidden Markov Models: it takes N1 to tango | 3 | 0.44 | 2009 |
| Deep Boltzmann Machines | 172 | 16.88 | 2009 |
| Workshop summary: Workshop on learning feature hierarchies | 1 | 0.35 | 2009 |
