Khashayar Khosravi

Learn More
Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling. However, all such models are based on the conventional classification framework, where model is trained against one-hot targets, and each word is represented both as an input and as an output in isolation. This causes inefficiencies in(More)
A Quality Model considering Program Architecture présenté par : Khashayar Khosravi a ´ etéévalué par le jury composé de : Esma A¨ımeur président–rapporteur Yann-Gaël Guéhéneuc directeur de recherche Houari Sahraoui membre du jury Mémoire accepté le To my Mom and Dad And also To my Sister and my Brother With all my love. And may we be among those who make(More)
We provide a unifying view of statistical information measures, multi-class classification problems, multi-way Bayesian hypothesis testing, and loss functions, elaborating equivalence results between all of these objects. In particular, we consider a particular generalization of f-divergences to multiple distributions, and we show that there is a(More)