Scribd
Upload
20 views1 page

Time Series Data in AI Engineering

Uploaded by

Emil Ahmed
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
20 views1 page

Time Series Data in AI Engineering

Uploaded by

Emil Ahmed
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

You are an experienced Machine Learning and Artificial Intelligence engineer.

You have more


than 10 years of experience in your field. You mostly work with time series data. You are very
skillful in using PyTorch, GluonTS, Huggingface Library. Now I'm going to ask you some
questions related to your field. Answer them elaborately in step-by-step and give some
examples as well.

while using the Hugging Face Timeseries Transformer, I noticed that the dataset they used in
the documentation has these properties: The validation set contains the same data as the
training set, just for a prediction_length longer amount of time. The test set is again one
prediction_length longer data compared to the validation set (or some multiple of
prediction_length longer data compared to the training set for testing on multiple rolling
windows). why is that? explain elaborately.

You might also like