| 8-Bit Approximations for Parallelism in Deep Learning |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
✅ |
5 |
| A Test of Relative Similarity for Model Selection in Generative Models |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| A note on the evaluation of generative models |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| ACDC: A Structured Efficient Linear Layer |
❌ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
5 |
| Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| Adversarial Manipulation of Deep Representations |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| All you need is a good init |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
4 |
| An Exploration of Softmax Alternatives Belonging to the Spherical Loss Family |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Auxiliary Image Regularization for Deep CNNs with Noisy Labels |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Bayesian Representation Learning with Oracle Constraints |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Better Computer Go Player with Neural Network and Long-term Prediction |
❌ |
❌ |
✅ |
❌ |
✅ |
✅ |
✅ |
4 |
| BlackOut: Speeding up Recurrent Neural Network Language Models With Very Large Vocabularies |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
6 |
| Censoring Representations with an Adversary |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Continuous control with deep reinforcement learning |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Convergent Learning: Do different neural networks learn the same representations? |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Convolutional Neural Networks With Low-rank Regularization |
❌ |
✅ |
✅ |
✅ |
✅ |
✅ |
✅ |
6 |
| Data Representation and Compression Using Linear-Programming Approximations |
❌ |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
4 |
| Data-Dependent Path Normalization in Neural Networks |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
0 |
| Data-dependent initializations of Convolutional Neural Networks |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Deep Linear Discriminant Analysis |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Deep Multi Scale Video Prediction Beyond Mean Square Error |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Deep Reinforcement Learning in Parameterized Action Space |
❌ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
4 |
| Delving Deeper into Convolutional Networks for Learning Video Representations |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Density Modeling of Images using a Generalized Normalization Transformation |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Digging Deep into the layers of CNNs: In Search of How CNNs Achieve View Invariance |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
2 |
| Distributional Smoothing with Virtual Adversarial Training |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Diversity Networks |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| Evaluating Prerequisite Qualities for Learning End-to-end Dialog Systems |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Gated Graph Sequence Neural Networks |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Generating Images from Captions with Attention |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Geodesics of learned representations |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Grid Long Short-Term Memory |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| High-Dimensional Continuous Control Using Generalized Advantage Estimation |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| Importance Weighted Autoencoders |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Large-Scale Approximate Kernel Canonical Correlation Analysis |
✅ |
✅ |
✅ |
✅ |
✅ |
❌ |
✅ |
6 |
| Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks |
❌ |
✅ |
❌ |
✅ |
❌ |
❌ |
✅ |
3 |
| Learning VIsual Predictive Models of Physics for Playing Billiards |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
1 |
| Learning to Diagnose with LSTM Recurrent Neural Networks |
❌ |
❌ |
❌ |
✅ |
✅ |
❌ |
✅ |
3 |
| Metric Learning with Adaptive Density Discrimination |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Modeling Visual Representations:Defining Properties and Deep Approximations |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
0 |
| MuProp: Unbiased Backpropagation For Stochastic Neural Networks |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Multi-Scale Context Aggregation by Dilated Convolutions |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Multi-task Sequence to Sequence Learning |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Net2Net: Accelerating Learning via Knowledge Transfer |
✅ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Neural GPUs Learn Algorithms |
❌ |
✅ |
❌ |
❌ |
✅ |
❌ |
✅ |
3 |
| Neural Networks with Few Multiplications |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Neural Programmer-Interpreters |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Neural Programmer: Inducing Latent Programs with Gradient Descent |
✅ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
2 |
| Neural Random-Access Machines |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
1 |
| Order Matters: Sequence to sequence for sets |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Order-Embeddings of Images and Language |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Particular object retrieval with integral max-pooling of CNN activations |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Policy Distillation |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Predicting distributions with Linearizing Belief Networks |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Prioritized Experience Replay |
✅ |
❌ |
✅ |
❌ |
❌ |
✅ |
✅ |
4 |
| Pushing the Boundaries of Boundary Detection using Deep Learning |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| Reasoning about Entailment with Neural Attention |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Reasoning in Vector Space: An Exploratory Study of Question Answering |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
❌ |
1 |
| Recurrent Gaussian Processes |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |
| Reducing Overfitting in Deep Networks by Decorrelating Representations |
❌ |
❌ |
✅ |
✅ |
❌ |
✅ |
✅ |
4 |
| Regularizing RNNs by Stabilizing Activations |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Segmental Recurrent Neural Networks |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Sequence Level Training with Recurrent Neural Networks |
✅ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
5 |
| Session-based recommendations with recurrent neural networks |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| SparkNet: Training Deep Networks in Spark |
✅ |
✅ |
✅ |
❌ |
✅ |
❌ |
✅ |
5 |
| Super-resolution with deep convolutional sufficient statistics |
❌ |
❌ |
✅ |
❌ |
✅ |
❌ |
✅ |
3 |
| The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| The Variational Fair Autoencoder |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
❌ |
3 |
| Towards Universal Paraphrastic Sentence Embeddings |
❌ |
✅ |
✅ |
✅ |
❌ |
❌ |
✅ |
4 |
| Training Convolutional Neural Networks with Low-rank Filters for Efficient Image Classification |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Unifying distillation and privileged information |
❌ |
✅ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks |
❌ |
❌ |
✅ |
✅ |
✅ |
❌ |
✅ |
4 |
| Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks |
❌ |
❌ |
✅ |
✅ |
❌ |
❌ |
✅ |
3 |
| Variable Rate Image Compression with Recurrent Neural Networks |
❌ |
❌ |
❌ |
❌ |
❌ |
❌ |
✅ |
1 |
| Variational Gaussian Process |
✅ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
3 |
| Variationally Auto-Encoded Deep Gaussian Processes |
❌ |
❌ |
✅ |
❌ |
❌ |
❌ |
✅ |
2 |