Anomaly Detection using Variational Autoencoder LSTM

Authors: Jonas Søbro Christophersen & Lau Johansson

This repository contains hand-in assignment for the DTU course 02460 Advanced Machine Learning.

This notebook is a implementation of a variational autoencoder which can detect anomalies unsupervised.

It is inspired by the approach proposed by J. Pereira and M. Silveira in paper "Unsupervised Anomaly Detection in Energy Time Series Data Using Variational Recurrent Autoencoders with Attention". Find it here

The code has taken inspiration in Pytorch's VAE example

Read our article here
Look at the implemented model here