DeepAI AI Chat
Log In Sign Up

Tutorial on Variational Autoencoders

06/19/2016
by   Carl Doersch, et al.
0

In just three years, Variational Autoencoders (VAEs) have emerged as one of the most popular approaches to unsupervised learning of complicated distributions. VAEs are appealing because they are built on top of standard function approximators (neural networks), and can be trained with stochastic gradient descent. VAEs have already shown promise in generating many kinds of complicated data, including handwritten digits, faces, house numbers, CIFAR images, physical models of scenes, segmentation, and predicting the future from static images. This tutorial introduces the intuitions behind VAEs, explains the mathematics behind them, and describes some empirical behavior. No prior knowledge of variational Bayesian methods is assumed.

READ FULL TEXT

page 6

page 17

page 18

06/06/2019

An Introduction to Variational Autoencoders

Variational autoencoders provide a principled framework for learning dee...
05/29/2020

Bayesian Neural Network via Stochastic Gradient Descent

The goal of bayesian approach used in variational inference is to minimi...
02/01/2019

A Classification Supervised Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids

Classic Autoencoders and variational autoencoders are used to learn comp...
08/01/2018

Subitizing with Variational Autoencoders

Numerosity, the number of objects in a set, is a basic property of a giv...
06/11/2021

Model Selection for Bayesian Autoencoders

We develop a novel method for carrying out model selection for Bayesian ...
04/20/2018

Inter-Annotator Agreement Networks

This work develops a simple information theoretic framework that capture...

Code Repositories

pytorch-vae

A Variational Autoencoder (VAE) implemented in PyTorch


view repo

latent_factor_disentanglement

None


view repo

Var_AutoEncoder-VAE-

From here-Tutorial on AutoEncoders. https://arxiv.org/abs/1606.05908


view repo

vae

Variational Auto Encoder implementation in PyTorch with latent space representation


view repo