Fig. 1From: Boosting for high-dimensional two-class predictionSchematic presentation of the AdaBoost.M1.ICV. With L we denote the training set, n is the size of the training set, m denotes the boosting iteration (m=1,…,M). For the m-th boosting iteration: \({w_{m}^{i}}\) are the case-specific weights for sample i, c m is a base classifier, \({\epsilon _{m}^{i}}\) is the cross-validated error for sample i, ε m is the cross-validated error, α m denotes the classifier-specific weight and y m is predicted class for a new sample at iteration m Back to article page