| I05-2033 | boosting algorithm requires a | weak learning algorithm | whose error is bounded by a constant |
| W07-1410 | highly accurate prediction rule . A | weak learning algorithm | is used to find the weak rules |
| P97-1030 | predictor by iteratively calling a | weak learning algorithm | ( that is slightly better than |
| E97-1030 | predictor by iteratively calling a | weak learning algorithm | ( that is slightly better than |
| W01-0721 | significantly reduce the error of any | weak learning algorithm | . While the AdaBoost algorithm |
| W99-0613 | AdaBoost is given access to a | weak learning algorithm | , which accepts as input the |
| N04-1026 | decision tree learner as AdaBoost 's | weak learning algorithm | . To investigate how well our |
| I05-2033 | improving the performance of a | weak learning algorithm | . AdaBoost changes the weights |
| W06-3005 | t = 1 , ... , T. Each time the | weak learning algorithm | generates a rough " rule of thumb |
| W06-3005 | over-fitting . It calls a given | weak learning algorithm | repeatedly in a series of rounds |
