OpenAI:generative-models blogs
来源:互联网 发布:虾米音乐vip 知乎 编辑:程序博客网 时间:2024/06/05 09:03
Three approaches to generative models
Most generative models have this basic setup, but differ in the details. Here are three popular examples of generative model approaches to give you a sense of the variation:
Generative Adversarial Networks (GANs), which we already discussed above, pose the training process as a game between two separate networks: a generator network (as seen above) and a second discriminative network that tries to classify samples as either coming from the true distribution
Variational Autoencoders (VAEs) allow us to formalize this problem in the framework of probabilistic graphical models where we are maximizing a lower bound on the log likelihood of the data.
Autoregressive models such as PixelRNN instead train a network that models the conditional distribution of every individual pixel given previous pixels (to the left and to the top). This is similar to plugging the pixels of the image into a char-rnn, but the RNNs run both horizontally and vertically over the image instead of just a 1D sequence of characters.
All of these approaches have their pros and cons. For example, Variational Autoencoders allow us to perform both learning and efficient Bayesian inference in sophisticated probabilistic graphical models with latent variables (e.g. see DRAW, or Attend Infer Repeat for hints of recent relatively complex models). However, their generated samples tend to be slightly blurry. GANs currently generate the sharpest images but they are more difficult to optimize due to unstable training dynamics. PixelRNNs have a very simple and stable training process (softmax loss) and currently give the best log likelihoods (that is, plausibility of the generated data). However, they are relatively inefficient during sampling and don’t easily provide simple low-dimensional codes for images. All of these models are active areas of research and we are eager to see how they develop in the future!
OpenAI generative models blog
- OpenAI:generative-models blogs
- Generative vs Discriminative Models
- Generative vs. Discriminative Models
- CS231N-13-Generative Models
- Discrimination Models , Generative Models and Naive Bayes
- CS231n学习笔记--13. Generative Models
- #DeepLearningBook#算法概览之十:Deep Generative Models
- MLaPP Chapter 3: Generative models for distrete data
- Blogs
- blogs
- blogs
- blogs
- DeepMind one shot learning 论文批注 One-Shot Generalization in Deep Generative Models
- 行人属性“Generative Adversarial Models for People Attribute Recognition in Surveillance”
- OpenAI教程
- OpenAI gym
- OpenAI Gym1
- OpenAI Gym2
- oracle database 11g安装linux系统参数要求
- extjs6.2中Ext.DomHelper类与Ext.XTemplate类初探
- 不同中奖概率的多奖包抽奖几种算法
- java之常用API(二)
- Oracle集群断电恢复实例(续)
- OpenAI:generative-models blogs
- C++ 解析flv文件
- C10K问题
- jQuery is not defined
- EOJ 1802 铁路调度
- 普通服务器与负载均衡服务器下的$_SERVER变量对比
- PopupWindow,DatePickerDialog,TimePickerDialog,ProgressDialog的使用
- Android 获取验证码使用倒计时
- 链表的引入和简单应用