amd_best's profile - activity

2013-05-28 07:52:46 -0600	commented question	adaboost features selection from large pool i want create a ranking of most important features of pedestrian , the pool is very large because i use a features simil to haar, and i can generate a large pool of features, the lenght of vector features descriptor is 10^6 byte
2013-05-28 04:20:22 -0600	received badge	● Student (source)
2013-05-28 03:43:01 -0600	received badge	● Editor (source)
2013-05-28 03:41:59 -0600	asked a question	adaboost features selection from large pool Hi, I want to train adaboost with 10^9 features but it can't stay all to gheter in memory , i procedeed with this approch: for(i=1 to 1000) { -load 10^6 features from the 10^9 pool -select the best 1 features and store it } but if i test the strong classifier on validation set i have results(correct detection-false positive) worst then this approches: -load 10^6 features from the 10^9 pool -select the best 1000 features and store it i think the first approches is more exaustive then the second but the second is better on validation set, someone can tell me anything about this anomaly?