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 convolutions Discriminator 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:**