In this paper we investigate a number of ensemble methods for improving the performance of phoneme classiication for use in a speech recognition system. We discuss boosting and mixtures of experts, both in isolation and in combination. We present results on an isolated word database. The results show that principled ensemble methods such as boosting and mixtures provide superior performance to ...

Boosting combines weak classifiers to form highly accurate predictors. Although the case of binary classification is well understood, in the multiclass setting, the “correct” requirements on the weak classifier, or the notion of the most efficient boosting algorithms are missing. In this paper, we create a broad and general framework, within which we make precise and identify the optimal requir...

This paper compares the performance of Boosting and nonBoosting training algorithms in large vocabulary continuous speech recognition (LVCSR) using ensembles of acoustic models. Both algorithms demonstrated significant word error rate reduction on the CMU Communicator corpus. However, both algorithms produced comparable improvements, even though one would expect that the Boosting algorithm, whi...

We describe, analyze and experiment with a boosting algorithm for multilabel categorization problems. Our algorithm includes as special cases previously studied boosting algorithms such as Adaboost.MH. We cast the multilabel problem as multiple binary decision problems, based on a user-defined covering of the set of labels. We prove a lower bound on the progress made by our algorithm on each bo...

The relation of the Al-Alaoui pattern recognition algorithm to the boosting and bagging approaches to pattern recognition is delineated. It is shown that the Al-Alaoui algorithm shares with bagging and boosting the concepts of replicating and weighting instances of the training set. Additionally it is shown that the Al-Alaoui algorithm provides a Mean Square Error, MSE, asymptotic Bayesian appr...

This paper describes our system for humor ranking in tweets within the SemEval 2017 Task 6: #HashtagWars (6A and 6B). For both subtasks, we use an off-the-shelf gradient boosting model built on a rich set of features, handcrafted to provide the model with the external knowledge needed to better predict the humor in the text. The features capture various cultural references and specific humor pa...

The probability of error of classification methods based on convex combinations of simple base classifiers by “boosting” algorithms is investigated. We show in this talk that certain regularized boosting algorithms provide Bayes-risk consistent classifiers under the only assumption that the Bayes classifier may be approximated by a convex combination of the base classifiers. Non-asymptotic dist...

Several authors have suggested viewing boosting as a gradient descent search for a good fit in function space. We apply gradient-based boosting methodology to the unsupervised learning problem of density estimation. We show convergence properties of the algorithm and prove that a strength of weak learnability property applies to this problem as well. We illustrate the potential of this approach...