CS231n学习笔记--13. Generative Models
来源:互联网 发布:java经典编程题 编辑:程序博客网 时间:2024/06/05 01:55
1. Unsupervised Learning
Supervised vs Unsupervised Learning:
2. Generative Models
概述:
**Generative Models的作用:**
**Generative Models的分类:**
3. PixelRNN and PixelCNN
基本原理:
**PixelRNN:**
**PixelCNN:**
Training is faster than PixelRNN (can parallelize convolutions since context region values known from training images)Generation must still proceed sequentially=> still slow**Generation Samples:**
**PixelRNN and PixelCNN**
4. Variational Autoencoders (VAE)
4.1 与PixelRNN/PixelCNN的比较:
**4.2 Some background first: Autoencoders:**
**Tips:**如果将其用于特征提取,则在训练之后,将decoder部分丢弃!
Autoencoders can reconstruct data, and can learn features to initialize a supervised model!**4.3 Variational Autoencoders**
利用高斯分布随机生成特征Z:
**Variational Autoencoders: Intractability**pθ(z) 跟据高斯分布随机获得,pθ(x|z) 根据decoder net获得,而为每个z计算pθ(x|z) 并最终积分得到pθ(x) 是不可能的!解决办法:
如何进行优化:
**4.4 Generating Data!**
**4.5 性能分析:**
5. Generative Adversarial Networks (GAN)
回顾:
**5.1 Training GANs: Two-player game****Generator network:** try to fool the discriminator by generating real-looking images**Discriminator network:** try to distinguish between real and fake images
网络优化:
优化存在的问题:
解决办法:
GAN training algorithm:
5.2 Generative Adversarial Nets
Generated samples:
**Generative Adversarial Nets: Convolutional Architectures**Generator is an upsampling network with fractionally-strided convolutionsDiscriminator is a convolutional network
Generator网络结构:
Samples from the model look amazing!
**Generative Adversarial Nets: Interpretable Vector Math**
**GANs的优缺点:**
6. 回顾:
阅读全文
0 0
- CS231n学习笔记--13. Generative Models
- CS231N-13-Generative Models
- Generative vs Discriminative Models
- Generative vs. Discriminative Models
- OpenAI:generative-models blogs
- CS231n 学习笔记
- CS231n学习笔记
- models数据模型学习笔记
- Discrimination Models , Generative Models and Naive Bayes
- 深度学习:CS231n官方笔记
- 斯坦福CS231N机器学习笔记
- 斯坦福CS231N课程学习笔记
- 深度学习:CS231n官方笔记
- CS231n学习笔记--Assignment2/3
- <转载>CS231n课程学习笔记
- CS231n学习笔记-1.Python&Numpy学习
- CS231N学习笔记0 学习环境配置
- CS231N 卷积神经网络课程学习笔记
- A
- SharePoint Framework 基于团队的开发(二)
- freemarker 下拉框回显
- 对线性回归、逻辑回归、各种回归的概念学习
- 关于使用EasyUI动态添加标签的个人笔记-V1
- CS231n学习笔记--13. Generative Models
- 编译原理入门
- ThinkPHP3.2判断手机端访问并设置默认访问模块的方法
- 执行nginx -s reload报错
- 【C++】去除数组中的某数且不使用额外空间
- phpStudy for Linux (lnmp+lamp一键安装包)
- 数据结构之树
- JS----实用小知识-------对表格 增删 行操作
- TP3.2:上传预览+缩略图+水印实例