# 概率与信息论

* [返回顶层目录](https://github.com/luweikxy/machine-learning-notes/tree/e6846dd98ccc8c039dcc79a4a5a4b198a1c9952f/content/content/SUMMARY.md#目录)
* [综述概率论基本定义](/machine-learning-notes/statistics-and-information-theory/review-of-statistics.md)
* [概率论与贝叶斯先验](/machine-learning-notes/statistics-and-information-theory/probability-and-bayesian-prior.md)
* [贝叶斯概率](/machine-learning-notes/statistics-and-information-theory/bayes-probability.md)
* [概率符号说明](/machine-learning-notes/statistics-and-information-theory/probability-symbol-explaination.md)
* [共轭先验](/machine-learning-notes/statistics-and-information-theory/conjugate-prior.md)

概率论使我们能够提出不确定的声明，以及在不确定性存在的情况下进行推理，而信息论使我们能够量化概率分布中的不确定性总量。（《深度学习》p34）

中心极限定理和大数定律

中心极限定理是说无论抽样分布如何 均值服从正态分布 而大数定律根本和正态分布无关 是说样本大了抽样分布近似总体分布

[怎样理解和区分中心极限定理与大数定律？ - 知乎](https://www.zhihu.com/question/22913867/answer/274009483)

[F分布、t分布、正太分布与卡方分布的联系与区别](https://zhuanlan.zhihu.com/p/42136925)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://luweikxy.gitbook.io/machine-learning-notes/statistics-and-information-theory.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.