Variational Autoencoder From Scratch This repository explores the design, training, experiments and theorical foundations of auto-encoders and variational autoencoders (VAE). The goal is to show how ...
A variational autoencoder (VAE) is one of several generative models that use deep learning to generate new content, detect anomalies and remove noise. Suited for generating synthetic time series data ...
This repository contains a simple implementation of 2D convolutional autoencoders. This Jupyter Notebook demonstrates a vanilla autoencoder (AE) and the variational (VAE) version is in this notebook.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results