Speeding up AdaBoost Classifier with Random Projection

摘要: The development of techniques for scaling up classifiers so that they can be applied to problems with large datasets training examples is one the objectives data mining. Recently, AdaBoost has become popular among machine learning community thanks its promising results across a variety applications. However, on major problem, especially when dimensionality very high. This paper discusses effect high process AdaBoost. Two preprocessing options reduce dimensionality, namely principal component analysis and random projection are briefly examined. Random subject probabilistic length preserving transformation explored further as computationally light step. experimental obtained demonstrate effectiveness proposed handling dimensional datasets.