An autoencoder is a type of artificial neural network used to learn efficient codings of unlabeled data (unsupervised learning). The encoding is validated and refined by attempting to regenerate the ...
An autoencoder can be used to detect anomalies through the reconstruction error (anomaly score). The way it works, is that given and initial set of observations, the ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback