5,337
edits
Deep Learning: Difference between revisions
→Variational Autoencoders (VAE)
| Line 936: | Line 936: | ||
==Variational Autoencoders (VAE)== | ==Variational Autoencoders (VAE)== | ||
Deep generative models: | |||
Given training data <math>\{x_i\}_{i=1}^{n}</math>. | |||
The goal is to ''generate'' realistic fake samples. | |||
Given a good generative model, we can do denoising, inpainting, domain transfer, etc. | |||
Probabilistic Model: | |||
suppose our dataset is <math>\{x_i\}_{1}^{n}</math> with <math>x_i \in \mathbb{R}^d</math> | |||
# Generate latent variables <math>z_1,...,z_n \in \mathbb{R}^r</math> where <math>r << d</math>. | |||
# Assume <math>X=x_i | Z = z_i \sim N \left( g_{theta}(z_i), \sigma^2 I \right)</math> | |||
==Misc== | ==Misc== | ||