机器学习人工学weekly-2018/9/9

注意下面很多链接需要访问外国网站，无奈国情如此

1. 多目标优化neural architecture search

Searching toward pareto-optimal device-aware neural architectures

链接：

https://arxiv.org/pdf/1808.09830.pdf

2. GAN Lab，浏览器里玩GAN，挺酷的

链接：

https://poloclub.github.io/ganlab/

3. Facebook无监督翻译

Unsupervised machine translation: A novel approach to provide fast, accurate translations for more languages

链接：

https://code.fb.com/ai-research/unsupervised-machine-translation-a-novel-approach-to-provide-fast-accurate-translations-for-more-languages/?utm_campaign=ARCHITECHT&utm_medium=email&utm_source=ARCHITECHT_67

4. RL概述文

A (Long) Peek into Reinforcement Learning

链接：

https://lilianweng.github.io/lil-log/2018/02/19/a-long-peek-into-reinforcement-learning.html

5. RL大神Pieter Abbeel新deck

链接：

https://www.dropbox.com/s/0cs3s55hsuba0ra/2018_08_13__Deep-Learning-to-Learn__GaTech__Abbeel--final.pdf?dl=0&utm_campaign=Artificial%2BIntelligence%2BWeekly&utm_medium=email&utm_source=Artificial_Intelligence_Weekly_85

6. 各种VAE简介

From Autoencoder to Beta-VAE

链接：

https://lilianweng.github.io/lil-log/2018/08/12/from-autoencoder-to-beta-vae.html

7. gradient boosting介绍

How to explain gradient boosting

链接：

http://explained.ai/gradient-boosting/index.html?utm_campaign=Deep%20Learning%20Weekly&utm_medium=email&utm_source=Revue%20newsletter

8. BAIR博文，用想象的目标做RL

Visual Reinforcement Learning with Imagined Goals

链接：

https://bair.berkeley.edu/blog/2018/09/06/rig/

9. 百度发布EZDL，免费，而且是custom model，AutoML的感觉

链接：

http://ai.baidu.com/ezdl/

10. RL 60天培训班资料

链接：

https://github.com/andri27-ts/60_Days_RL_Challenge