Discriminative model: The conditional probability of class label on data (posterior) $p(C_k\mid x)$ …

The likelihood is modeled as $$ \begin{align} p_\theta (x) &= \Pi_{t=1}^T p_\theta (x_t \mid …

For a probability density $p(x)$ and a transformation of coordinate $x=g(z)$ or $z=f(x)$, the …

The simplest auto-encoder is rather simple. The loss can be chosen based on the demand, e.g., …

Variational Auto-Encoder (VAE) is very different from Generative Model: Auto-Encoder Generative …