How to use the Extrapolate library in NanoEdge AI studio

[szxx]

I encountered two problems while learning the Extrapolate library:
One of the issues is that I am not very clear about this extrapolation value, and I don't know if there is a problem understanding it. I have always believed that this extrapolated value is a predicted data value made by AI after reading the raw data of my sensor and predicting the trend of sensor changes. However, while studying, I found that this value seemed to need to be set by myself, which made me very confused.
Another question that I derived from the first one is that I am not sure what kind of data should be included in Add Singal. In my personal understanding, if I have two columns of data, is the first column the predicted value I set myself? Is the second column my original sequence?
Then I tried to search for information in comments and online, but I found that I still couldn't find more information about the Extrapolate library in this NanoEdge AI studio. If you know, can you help me solve these two confusions?
Thank you very much for your help. Wishing everyone a happy life and good health!

[Julian E.]

Hello @szxx,

You can find more information about the extrapolation format here:

https://wiki.st.com/stm32mcu/wiki/AI:NanoEdge_AI_Studio#Variant_format-_Extrapolation_projects

I am not sure to understand your first question correctly, but the goal of the extrapolation project (regression) is that in training you provide data and a label value (in first column), for example:

price of a home | size | number of rooms | location etc

then once train, you provide data without the label, and it is the model that predict the label (the price of the home in this example).

To train the best model possible, it is advised to use training model as variate as possible with widest range of labels.

If I take my previous example, if the prices of the homes go from 100k to 1m for example, it is best to have test data in the same range. The model performs well if it has example in training in the same range as the test data.

Let me know if you need anything else.

Have a good day,

Julian