Choose timezone
Your profile timezone:
Summary:
1. Matt presented the BDT results of the gamma vs. pi0 classifier. ECALmomentY5 still contributed more than ECALmomentX5 (without adding subjettiness).
2. Doubling the training sample size for electron vs. charged pion classifier to 400K did not increase the accuracy. Maybe we need more training data?
3. A faster generator will be released.
4. We also debugged the code for subjettiness.