机器学习人工学weekly-2018/5/13

1. Google I/O召开大会，个人觉得最有意思的是TPU 3.0和AI冒充真人打电话

1. 1 Google Duplex: An AI System for Accomplishing Real World Tasks Over the Phone

链接：https://ai.googleblog.com/2018/05/duplex-ai-system-for-natural-conversation.html

1. 2 ML Kit

链接：https://developers.google.com/ml-kit/

2. DeepMind

2.1 DeepMind发到Nature上最新的工作, grid cell

Navigating with grid-like representations in artificial agents

链接：https://deepmind.com/blog/grid-cells/

2.2 在今年ICLR上的论文

链接：https://deepmind.com/blog/deepmind-papers-iclr-2018/?utm_campaign=Revue%20newsletter&utm_medium=Newsletter&utm_source=Deep%20Learning%20Weekly

2.3 DeepMind帮安卓优化电池

DeepMind, meets Android

链接：https://deepmind.com/blog/deepmind-meet-android/?utm_campaign=ARCHITECHT&utm_medium=email&utm_source=ARCHITECHT_25

3. 名校课程

3.1 哈佛CS109数据科学课程

链接：http://cs109.github.io/2015/index.html

3.2 伯克利CS189机器学习课程

链接：https://www.eecs189.org/

4. Facebook短视频介绍ML

Facebook’s Field Guide to Machine Learning video series

链接：https://research.fb.com/the-facebook-field-guide-to-machine-learning-video-series/

5. meta-learning: 遗传算法学模型超参简介

Genetic Algorithms + Neural Networks = Best of Both Worlds

链接：https://towardsdatascience.com/gas-and-nns-6a41f1e8146d

6. active learning框架

链接：https://cosmic-cortex.github.io/modAL/

7. CNN详解

Convolutional Neural Networks: The Biologically-Inspired Model

链接：https://www.codementor.io/james_aka_yale/convolutional-neural-networks-the-biologically-inspired-model-iq6s48zms

8. 神经网络可视化工具

Visualizing Artificial Neural Networks (ANNs) with just One Line of Code

链接：https://towardsdatascience.com/visualizing-artificial-neural-networks-anns-with-just-one-line-of-code-b4233607209e

9. Restricted Boltzmann Machines的解释

Deep Learning meets Physics: Restricted Boltzmann Machines

链接：https://towardsdatascience.com/deep-learning-meets-physics-restricted-boltzmann-machines-part-i-6df5c4918c15