#

VAE

A variational autoencoder (VAE) is a generative model that combines deep learning with Bayesian inference to learn compact latent representations of data. VAEs are widely used for image generation, anomaly detection, and data augmentation.

Here are 5 public repositories matching this topic...

cam1681 / CS25_Large_Foundation_model

Lecture slides for the Course "Large Foundation Models: Mathematics, Algorithms, and Applications"

flow course vae rl partial-differential-equations auto-regressive-model stochastic-processes diffusion ai4science llm

Updated Feb 3, 2026
TeX

faltysad / bachelor-thesis-text

Variational autoencoder is an innovation in the field of unsupervised machine learning. Its architecture combines stochastic encoder-decoder modules and deep learning.

machine-learning latex vae latent-variable-models

Updated May 10, 2023
TeX

Melika-Ayoughi / Deep-Learning-UvA

Deep learning assignments of master course taught by Efstratios Gavves at UvA university

pytorch lstm gan rnn vae mlp normalizing-flows

Updated Jun 20, 2019
TeX

exbibyte / coursework_prob_learning

archived content from probabilistic learning course

vae probabilistic-inference

Updated Apr 11, 2020
TeX

lorenzo677 / PPG

Project for Pattern Recognition and Physical Methods for Biology exams @ University of Bologna

python machine-learning vae variational-autoencoder tensorflow2

Updated Dec 23, 2022
TeX

Followers: 10 followers
Website: github.com/topics/vae
Wikipedia: Wikipedia