The problem of training classifiers from limited data is one that particularly affects large-scale and social applications, and as a result, although carefully trained machine learning forms the backbone of many current techniques in research, it sees dramatically fewer applications for end-users. Recently we demonstrated a technique for selecting or recommending a single good classifier from a large library even with highly impoverished training data. We consider alternatives for extending our recommendation technique to sets of classifiers, including a modification to the AdaBoost algorithm that incorporates recommendation. Evaluating on an action recognition problem, we present two viable methods for extending model recommendation to sets.
展开▼
