Here, I read the following:

The first key to understanding is that HTM relies on data that streams over time (...) By contrast, conventional deep learning uses static data and is therefore time invariant. Even RNN/LSTMs that process speech, which is time based, actually do so on static datasets.

On the other hand, on I read the following:

We can assert that our LSTM Autoencoder is a good weapon to extract importan unseen features from time series

What is true now? Are LSTM or autoencoders or combined suitable for time series analysis? Or is HTM better suited for that purpose, indeed?

The main purpose is to detect anomalies emerging through time before they happen.



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.