Even if a time series is constructed up of numbers only, finding abstract fixed-dim vector representation would be interesting for classification/clustering purposes. As we can learn & find abstract representations/embeddings of text/images, can we do something similar on Time series? Finding such ways would result in better clustering & related tasks instead of traditional ways using some statistical measures like Pearson correlation etc. All thoughts are welcome.

  • $\begingroup$ Have you heard of time-series segmentation algorithms? These seem to be what you are looking for. $\endgroup$
    – Edmund
    Commented Apr 18, 2019 at 2:31
  • $\begingroup$ **Thanks @Edmund **, I hadn't heard that before; but now I have learned about it.This is similar to what I am looking for, but still not exact match. A survey on TS segmentation $\endgroup$ Commented Apr 18, 2019 at 6:44

1 Answer 1


Maybe the framework of Neural Processes could be interesting here? It defines a family of functions parameterized by a neural network. The parameters could serve as your embeddings, eventually after projecting into a lower dimension. See the paper Attentive Neural Processes and the preceding papers cited therein.


Your Answer

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

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