I feel in the learning process, encountered do not understand, often need to review the probability theory of knowledge, so assume the machine learning nouns are mastered.
The following articles are the first big time feel read once you can understand. The basis of probability theory
Prior probability, posterior probability, Bayesian rule, maximal posterior probability hypothesis, maximum likelihood hypothesis Bayesian Bayesian learning – Maximum posterior probability hypothesis and maximum likelihood assumption mixed random variable expectation method and application calculus, linear algebra basis multivariate function for extremum problem positive definite matrix-Baidu Encyclopedia generation model vs Discriminant model
Generated:
-generation model and discriminant model
-(EM algorithm) The EM algorithm, mixed Gaussian model
-from the maximum likelihood to the EM algorithm shallow solution
Discriminant: (Understanding the idea of maximum likelihood)
-Logistics regression recommended to see Zhou Zhihua machine Learn Watermelon Books
-Softmax regression-UFLDL
In short, before reading these things, I think the maximum likelihood, KL divergence is to be very familiar with the build model
Generating model diagrams
[VAE]
–[paper]
–[code (Pytorch-example)]
–[very intuitive understanding: Conditional variational Autoencoders]
–[from model to derivation: "Learning Notes" variational self-encoder (variational auto-encoder,vae)] [GAN]
–[paper]
–[code] [Dcgan]
–[paper]
–[code (pytorch-example)] [Wgan]
–[paper]
–[code (Pytorch)]
–[in simple and simple introduction: The Astounding Wasserstein GAN]