Dr. James McCaffrey of Microsoft Research provides full code and step-by-step examples of anomaly detection, used to find items in a dataset that are different from the majority for tasks like ...

The autoencoder Train() method is called, and progress is monitored every 100 epochs: Starting training epoch: 0 MSE = 1.6188 epoch: 100 MSE = 0.0028 epoch: 200 MSE = 0.0013 . . . epoch: 900 MSE = ...