A benchmarking experiment to see if a Mahalanobis autoencoder is better at detecting anomalies than a normal autoencoder.
fedoracy / automahalanobis Goto Github PK
View Code? Open in Web Editor NEWThis project forked from bflammers/automahalanobis
A PyTorch implementation of an autoencoder trained to minimize the Mahalanobis distance between input and reconstruction.