# Autoencoders
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/nathanhubens/Autoencoders)
**Autoencoders (AE)** are neural networks that aims to copy their inputs to their outputs. They work by compressing the input into a latent-space representation, and then reconstructing the output from this representation. This kind of network is composed of two parts :
1. **Encoder**: This is the part of the network that compresses the input into a latent-space representation. It can be represented by an encoding function _h=f(x)_.
2. **Decoder**: This part aims to reconstruct the input from the latent space representation. It can be represented by a decoding function _r=g(h)_.
<img src="https://nathanhubens.github.io/posts/images/autoencoders/AE.png" alt="drawing" width="750"/>
This notebook show the implementation of five types of autoencoders :
* Vanilla Autoencoder
* Multilayer Autoencoder
* Convolutional Autoencoder
* Regularized Autoencoder
* Variational Autoencoder
The explanation of each (except VAE) can be found [here](https://towardsdatascience.com/deep-inside-autoencoders-7e41f319999f)
没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
收起资源包目录
基于机器学习的人群异常检测内含数据集.zip (9个子文件)
Autoencoders-master
Variational Autoencoders.ipynb 567KB
README.md 1KB
Autoencoders.ipynb 298KB
2011-2012.xlsx 17KB
Crowd_Anomaly_Detection-master
trainer.npy 44.03MB
Crowd_Anomaly_Detection_.ipynb 56KB
.ipynb_checkpoints
Crowd_Anomaly_Detection_-checkpoint.ipynb 56KB
2017年有关于深度学习的异常检测论文.xlsx 30KB
README.md 31B
共 9 条
- 1
资源评论
小码蚁.
- 粉丝: 2525
- 资源: 4090
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功