28 June - 11 July 2019
1991 new papers
Etymo Newsletter provides the latest development in machine learning research,
including the most popular datasets and the most trending papers in the past two weeks.
If you like this newsletter, you can subscribe to our fortnightly newsletters here.
Fortnight Summary
Popular datasets include MNIST, ImageNet, CIFAR-10, KITTI, COCO, and CelebA. Our trending phrases are Age Estimation, Joint Neural, and Video Denoising. In our trending papers section, we include a paper on large scale GAN (BiBigGAN) for substantially improved representation learning performance, and one review paper and one benchmarking paper on reinforcement learning. In addition, we also include a further three review papers on deep learning and neural networks.Popular Datasets
Here are most mentioned datasets over the last two weeks.
| Name | Type | Number of Papers |
|---|---|---|
| MNIST | Handwritten Digits | 69 |
| ImageNet | Image Dataset | 41 |
| CIFAR-10 | Tiny Image Dataset in 10 Classes | 35 |
| KITTI | Autonomous Driving | 15 |
| COCO | Common Objects in Context | 12 |
| CelebA | Large-scale CelebFaces Attributes (CelebA) Dataset | 11 |
Trending Phrases
In this section, we present a list of phrases that appeared significantly more in this newsletter than the previous newsletters.
Etymo Trending
Presented below is a list of the most trending papers added in the last two weeks.
-
Large Scale Adversarial Representation Learning:
The authors show that progress in image generation quality translates to substantially improved representation learning performance. Their approach, BigBiGAN, builds upon the state-of-the-art BigGAN model, extending it to representation learning by adding an encoder and modifying the discriminator. -
Modern Deep Reinforcement Learning Algorithms:
This is a review paper that reviews DRL algorithms with a focus on their theoretical justification, practical limitations and observed empirical properties. -
Benchmarking Model-Based Reinforcement Learning:
This paper a wide collection of Model-Based Reinforcement Learning (MBRL) algorithms and propose over 18 benchmarking environments specially designed for MBRL. The authors benchmark these algorithms with unified problem settings, including noisy environments. The open source benchmark can be found here.