How can auto-encoders compute the reconstruction error for the new data?

Question

Autoencoders are used for unsupervised anomaly detection by first learning the features of the data set with mainly "normal" data points. Then new data can be considered anomalous if the new data has a large reconstruction error, i.e. it was hard to fit the features as in the normal data.

Even if the training is supervised by learning to reconstruct the same data, how is the reconstruction error computed for the new data?

Answer 1

It is computed just like in training. You take an MSE or something along these lines between the input and the output. You set a threshold for it. If new data's reconstruction error is higher than your threshold, then it is anomalous otherwise it isn't.