Can denoising autoencoders be used for anomaly detection on structured data?

I know I can use denoising autoencoders for anomaly detection on images, but I don't know if they can do it for structured data as well? If not, why?


When you run denoise auto-encoders or any process on image data, what you did first was to convert run image data on a structured dataset with RGB arrays arranged in a column-like order.

Which means you turned your image data into structured data and then you applied the denoise-autoencoders, this means that you used the autoencoders on structured data.

Actually, almost no process is done in unstructured data. They run on the structured version of the structured data.

So the answer is yes, the denoise autoencoders does anomaly detection on structured data.

| improve this answer | |
  • $\begingroup$ denoise auto-encoders use convolutional , CNNs also use convolutional too. But CNNs can't apply on structured data, such as iris data. Why? thanks $\endgroup$ – disney82231 May 1 '19 at 13:04

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.