Show pageOld revisionsBacklinksBack to top This page is read only. You can view the source, but not change it. Ask your administrator if you think this is wrong. ===== Data set partitioning ===== Train / Dev / Test set Traditionally: 60 / 20 / 20 Big Data (>1 mio cases): 95.5 / 0.4 / 0.1 Another problem: Make sure that dev and test set came from same distribution (e.g. user uploaded potato pictures vs. high res). data_mining/neural_network/partitioning.txt Last modified: 2017/08/19 20:16by phreazer