Trustworthy machine intelligence is a major goal pursued by humans. In order to achieve trusted intelligence, people are working hard to explore. This blog discusses the realization of trusted artificial intelligence from the perspective of interpretability and robustness. Because the interpretability and robustness in this article are different from the previous concepts, two words high-level and high-level are added.
This blog is long. At this stage, it is temporarily closed to the outside world. If you want to read, please contact me.
可信任机器智能是人类追求的一大目标。为了达到可信智能，人们正在努力探索中。本文从可解释性和鲁棒性出发，探讨可信任人工智能的实现。由于本文中的可解释性与鲁棒性，区别于从前的概念，故加上高阶与高级两个词。
本博客较长。在目前阶段，暂不对外开放。如想阅读，请联系我。
-----------------------------------
大家好，我来自fast lab。我开始不定时公开写作。这些写作主要通过两个渠道公布：一是FAST LAB官方网站；一是印象识堂（微信可访问）。欢迎大家订阅。谢谢！
FAST Lab的官方网址为：https://wanggrun.github.io/projects/fast
除此外，还可以关注我的小伙伴王广润：https://wanggrun.github.io/
王广聪： https://wanggcong.github.io/
石阳：https://www.linkedin.com/in/%E9%98%B3-%E7%9F%B3-381b521a4/
有时候这些网站打不开，请耐心多点几次。
多谢大家关注。