Jet Tagging studies for VBF Higgs -> WW -> 2l2nu Neural Network for JetTagging
Kind of NN
Up to now three different NN have been tested, each one with pros and cons:
- NN on single jet
- NN on a pair of jets with some information from the remaining jets
- NN on all pair of jet (the first 4 pt ordered pairs of jets)
Analysis steps
Common steps for all NN approaches
- Creation of a TTree to store everything needed to study Jet tagging efficiencies and performance.
Single Jet NN
- Creation of a TTree to create input variables for NN
- Training of the NN TMultiLayerPerceptron (H160WW2l sample)
- Test of the NN TMultiLayerPerceptron
- PostTraining of the NN TMultiLayerPerceptron
- Test of the NN in CMSSW (just a function) -> jet pair with maximum NN output
- bin code -> comparison between Pt max, Mjj max e NN max methods
Results
- Purity: given a VBF event, number of events with two right jets tagged / total number of VBF events. L2+L3 corrected jets (NN not yet trained, but old trained one reused)
* Purity:
given a VBF event, number of events with two right jets tagged / total number of VBF events. L2+L3 corrected jets (NN
re-trained )
Multi Pair Jet NN
Single Pair Jet NN
- Creation of a TTree to create input variables for NN
- Training of the NN TMultiLayerPerceptron (H160WW2l sample)
- root macro
- 24k events training + 6k events test
- output of the training is a set of weights.
- Test of the NN TMultiLayerPerceptron
- Test of the NN in CMSSW -> jet pair with maximum NN output
- bin code -> comparison between Pt max, Mjj max e NN max methods
Results
-
- L2+L3 energy correction samples
--
AndreaMassironi - 04 Mar 2009