## More in Papers

### taki0112/UGATIT

14 saves · 2019-07-30 · Official Tensorflow implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation - taki0112/UGATIT

### MelNet

6 min read · 14 saves · 2019-06-06 · Speaker: Bill Gates Daphne Koller Fei-Fei Li George Takei Jane Goodall Sal Khan Stephen Wolfram Stephen Hawking Text: A cramp is no small danger…

### Connections between Support Vector Machines, Wasserstein distance and gradient-penalty GANs

12 saves · 2019-10-15 · We generalize the concept of maximum-margin classifiers (MMCs) to arbitrary norms and non-linear functions. Support Vector Machines (SVMs) are a special case of MMC.…

### State Marginal Matching

2 min read · 12 saves · 2019-06-18 · Contributed Talks @ ICLR 2019 workshops on

### Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?

11 saves · 2019-09-23 · Hierarchical reinforcement learning has demonstrated significant success at solving difficult reinforcement learning (RL) tasks. Previous works have motivated the use of hierarchy by appealing…

### StanfordVL/MinkowskiEngine

10 saves · 2019-07-26 · Minkowski Engine is an auto-diff library for generalized sparse convolutions and high-dimensional sparse tensors - StanfordVL/MinkowskiEngine

### Panoptic Segmentation with UPSNet

2 min read · Paywall possible · 10 saves · 2019-07-21 · Vaishak V.Kumar · Combining Semantic and Instance Segmentation for Complete Scene Understanding

### Mesh R-CNN

10 saves · 2019-06-06 · Rapid advances in 2D perception have led to systems that accurately detect objects in real-world images. However, these systems make predictions in 2D, ignoring…

### avisingh599/reward-learning-rl

10 saves · 2019-04-18 · [arxiv 2019] End-to-End Robotic Reinforcement Learning without Reward Engineering - avisingh599/reward-learning-rl

### Up to two billion times acceleration of scientific simulations with deep neural architecture search

Jan 17th · Computer simulations are invaluable tools for scientific discovery. However, accurate simulations are often slow to execute, which limits their applicability to extensive parameter exploration,…

### Meta-Learning Deep Energy-Based Memory Models

2019-10-07 · We study the problem of learning associative memory -- a system which is able to retrieve a remembered pattern based on its distorted or…

### Latent ODEs for Irregularly-Sampled Time Series

2019-07-08 · Time series with non-uniform intervals occur in many applications, and are difficult to model using standard recurrent neural networks (RNNs). We generalize RNNs to…