# 神经网络

## 感知机：

![image-20200202110706332](/files/-M02m9NB3iwKHVTMI_u6)

最早的神经元是感知机，输入乘权重之和，根据threshold输出0/1。

但是感知机的阶跃性质，非常不利于网络学习。例如：Z的输出在0附近并发生改变时，结果从0->1，回头对nn的权重造成不好的影响，这种情况重复多次的话是非常不利于模型学习的。

![image-20200203101243624](/files/-M02m9NDCV9smNZw44CV)

如图，这样的s型神经元(sigmoid函数)就可以用在我们的学习算法中。

![image-20200203102510245](/files/-M02m9NFgbDlZWlgGxjO)

讲完了单个神经元的学习，先看看神经网络的概念：

![image-20200203102658487](/files/-M02m9NHpoMoNVJCTkJp)

## 梯度下降与反向传播

先记住几个标记。

![image-20200203224941511](/files/-M02m9NJW0QjpIxc8zfr)

![image-20200203225024577](/files/-M02m9NLCYlZTql28BEh)

![image-20200204000031002](/files/-M02m9NNRk1M5IlhigvY)


---

# 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://jon-xia.gitbook.io/workspace/ji-qi-xue-xi-8/deeplearning/basic/nn-and-nerve-cell.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.