Suppose you have two datasets which are supposed to be identical. For example MC production v1, MC production v2; data of yesterday, data of today. How to detect differences ? This is done typically by comparing rates, or manually defined histograms. How to do this in an automatized, Machine Learning way ? The objective will be to detect differences between two datasets, identical except for introduced manipulations. The RAMP platform allows participants to collaborate to achieve this goal.
To ease organisation, please register specifically for this session on that indico page .
Participants will use their laptop, where Anaconda should be installed, and need to register to the RAMP site.
Please check detailed instructions on the attached README file, preferably before the workshop. All inquiries concerning the RAMP should be sent to firstname.lastname@example.org.
This session will be in parallel with other sessions.