Causal Inference


强人工智能之路 The Way To Strong AI

The increasing expectations for strong AI have met with 3 fundamental obstacles:

  • Adaptability or robustness,
  • Explainability,
  • Unable to understand cause-effect connections.

All these three obstacles can be overcome with causal modeling tools. In this site, you will learn causal inference from Zero To All .

注: 我们的所有内容尽量使用 colab, google drive etc. 制作方便评论和更新. (All our materials will be created by colab, google drive etc. to facilitate comments and updating)

Software libraries, packages and tools for causal inference.

Tutorials

Learning topics of causal inference with end to end tutorials

Projects for causal inference, including competitions, e.g. ACIC Data Challenge.

News

Click on notebook on colab to see News, blogs about causal inference. 偏好故事性而不是学术性。


2019-08-17 ICML2019 会议论文, 第一个使用因果理解神经网络. 2019-08-16 https://deeplearn2019.irdta.eu 深度学习需要因果理论 DeepLearn 2019 will be a research training event with a global scope aiming at updating participants about the most recent advances in the critical and fast developing area of deep learning. 2019-08-15 https://colab.research.google.com/drive/18k4F5BlcdkAtGhgZcRAD6WC4_v75u1Lp chain graph 是赋予一般有向图因果语义的关键.2019-07-24 https://drive.google.com/open?id=1G8BLG_YmHBsIuEO-cpRT6U-ScXCvbzMd 回顾经典展望未来 of data science2019-05-14 https://github.com/rguo12/awesome-causality-data 因果推断的数据2019-04-27 https://github.com/rguo12/awesome-causality-algorithms 因果推断算法及其代码.2019-04-24 https://pypi.org/project/pytorchcv/ Pre-trained CV networks 妈妈再也不用担心我找不到训练好的网络了, 嘿嘿, CondenseNet will be used for casual inference.2019-04-15 The most important developments in data science of 2018 指出了2018是因果推断进入AI是重大进展。


Mini-Turing test

How can machines represent causal knowledge in a way that would enable them to access the necessary information swiftly, answer questions correctly, and do it with ease, as a human can?

How causal graphs will change the future?

Pearl: it will enable us to understand ourselves. To implement agency, to implement free will in a machine so that we can communicate better with machine. And by communicating better we gain a greater understanding of ourselves.