We introduce quadratically gated mixture of experts (QGME), a statistical model for multi-class nonlinear classification. The QGME is formulated in the setting of incomplete data,...
Abstract. In Machine Learning, ensembles are combination of classifiers. Their objective is to improve the accuracy. In previous works, we have presented a method for the generati...
Backpropagation, similar to most learning algorithms that can form complex decision surfaces, is prone to overfitting. This work presents classification-based objective functions, ...
Although memory-based classifiers offer robust classification performance, their widespread usage on embedded devices is hindered due to the device's limited memory resources...
Abstract. In this paper, we propose a new method for learning to rank. `Ranking SVM' is a method for performing the task. It formulizes the problem as that of binary classific...