# 去噪自动编码器

## 特性

Denoising Autoencoder，简称DAE

在训练样本中**加入随机噪声**，重构的目标是：不带噪声的样本数据

用自动编码器学习得到的模型重构出来的数据可以去除这种噪声，获得没有被噪声污染过的数据

## 构造噪声向量

对于每个样本向量 随机选择其中的一部分分量，将它们的值置为0，其他分量保持不变，得到的 带噪声向量为$$\hat x$$

## 优化目标

对输入向量x构造噪声向量$$\hat x$$，然后编码，然后解码，希望解码结果和原始x相似，这样训练结果就能用于去噪

$$
\begin{aligned}
min\frac{1}{l}\sum\_{i=1}^{l}L(x\_i,g\_{\theta}(h\_{\theta}(\hat x\_i)))
\end{aligned}
$$


---

# 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://im-qianuxn.gitbook.io/pytorch/ji-suan-ji/shen-du-xue-xi-li-lun/01/02.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.