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.
A variational inference method with accurate uncertainty estimation. It uses a new semi-implicit variational family built on neural networks and hierarchical distribution (ICML 2018).
Matlab Variational LSTM Autoencoder and Time Series Prediction for anomaly detection. Some code of my masters thesis. Download Link: https://pure.unileoben.ac.at/portal/files/6093740/AC16131071.pdf
This repository provides implementation of SciNet network described in arXiv:1807.10300v3
Heavy-Tailed distributions in Variational Autoencoder (VAE)
Unsupervised CAN-bus intrusion detection in MATLAB: a CNN-LSTM variational autoencoder with self-attention that predicts the next CAN frame. Pipelines for Car-Hacking, OTIDS, CICIoV2024, ROAD and SynCAN.