How to get vector representations(or embeddings) of time series?

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.

Topic embeddings deep-learning time-series

Category Data Science

1
answered at

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.

About

Geeks Mental is a community that publishes articles and tutorials about Web, Android, Data Science, new techniques and Linux security.