机器学习人工学weekly-2018/3/25

注意下面很多链接需要访问外国网站，无奈国情如此

1. Quoc Le大神(Google Brain)讲Neural Architecture Search（目测是去年NIPS视频?）

YouTube视频：https://www.youtube.com/watch?v=sROrvtXnT7Q

2. Google/DeepMind最新工作

2.1 用teacher agent教student agent更快更好的学policy

Kickstarting Deep Reinforcement Learning

链接：https://arxiv.org/pdf/1803.03835.pdf

2.2 看起来容易解释的neuron(e.g., cat neuron)其实也不是那么重要 :)

Understanding deep learning through neuron deletion

链接：https://deepmind.com/blog/understanding-deep-learning-through-neuron-deletion/

2.3 模型可解释性

The Building Blocks of Interpretability

链接：https://distill.pub/2018/building-blocks/

3. 进化算法的复苏

3.1 sentient.ai（貌似专注进化算法）

Evolution is the New Deep Learning

链接：https://www.sentient.ai/blog/evolution-is-the-new-deep-learning/

3.2 Uber发布VINE，neuroevolution可视化工具

VINE: An Open Source Interactive Data Visualization Tool for Neuroevolution

链接：https://eng.uber.com/vine/

3.3 进化计算的各种趣闻

The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities

链接：https://arxiv.org/pdf/1803.03453.pdf

4. 微软作了一个聚合各个DL framework对比的实验

Comparing Deep Learning Frameworks: A Rosetta Stone Approach

链接：https://github.com/ilkarman/DeepLearningFrameworks?utm_campaign=Data%2BElixir&utm_medium=email&utm_source=Data_Elixir_174

5. MCTS介绍（在AlphaGo的背景下），写的不错

Monte Carlo Tree Search – beginners guide

https://int8.io/monte-carlo-tree-search-beginners-guide/

6. 做一个简单的人脸解锁工具

How I implemented iPhone X’s FaceID using Deep Learning in Python.

链接：https://towardsdatascience.com/how-i-implemented-iphone-xs-faceid-using-deep-learning-in-python-d5dbaa128e1d

7. 自驾车的技术总结及整理

On machine learning and structure for mobile robots

链接：https://markusrw.github.io/articles/tldr-on-ml-and-structure-for-robotics/

8. 各种ML算法的starter code，还有NLP spaCy

链接：http://mlreference.com/