知识卡片
深度网络可参数化因果机制
因果图确定条件机制的输入父集后,可用神经网络表示复杂的条件分布参数。网络适合高维非线性,不意味着自动发现真实因果关系;结构、测量、训练支持和函数近似质量仍需分别论证。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
原书出处 · 1 处
- · 查看原书依据
modeling the causal Markov kernel with a deep neural net, which we know is flexible enough to work with high-dimensional features like pixels. In this section, I’ll demonstrate how to use deep neural nets to model the causal Markov kernels defined by a causal DAG.
参考来源
- 位置:《Causal AI》第05章《连接因果与深度学习》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-5.xhtml)
- 结论依据:摘录中关于深度网络可参数化因果机制的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:modeling the causal Markov kernel with a deep neural net, which we know is flexible enough to work with high-dimensional features like pixels. In this section, I’ll demonstrate how to use deep neural nets to model the causal Markov kernels defined by a causal DAG.