Abstract. Boosting methods are known to improve generalization performances of learning algorithms reducing both bias and variance or enlarging the margin of the resulting multi-cl...
Francesco Masulli, Matteo Pardo, Giorgio Sbervegli...
Cross validation can be used to detect when over tting starts during supervised training of a neural network; training is then stopped before convergence to avoid the overtting ...
Unconstrained face recognition is the problem of deciding if an image pair is showing the same individual or not, without having class specific training material or knowing anythi...
Phoneme posterior probabilities estimated using Multi-Layer Perceptrons (MLPs) are extensively used both as acoustic scores and features for speech recognition. In this paper we e...
Samuel Thomas, Patrick Nguyen, Geoffrey Zweig, Hyn...
The use of large speech corpora in example-based approaches for speech recognition is mainly focused on increasing the number of examples. This strategy presents some difficulties ...