Beginning Anomaly Detection Using

 Noise  Removal

In 

noise removal, there is constant background noise in the data set that must be filtered 

out. Imagine that you are at a party and you are talking to your friend. There is a lot of 

background noise, but your brain focuses on your friend’s voice and isolates it because 

that’s what you want to hear. Similarly, the model learns an efficient way to represent the 

original data so that it can reconstruct it without the anomalous interference noise.

This can also be a case where an image has been altered in some form, such as by 

having perturbations, loss of detail, fog, etc. The model learns an accurate representation 

of the original image and outputs a reconstruction without any of the anomalous 

elements in the image.