A Generalized Linear Joint Trained Framework for Semi-Supervised Learning of Sparse Features

The elastic net is among the most widely used types of regularization algorithms, commonly associated with problem supervised generalized linear model estimation via penalized maximum likelihood. Its attractive properties, originated from a combination ?1 and ?2 norms, endow this method ability to select variables, taking into account correlations between them. In last few years, semi-supervised approaches that use both labeled unlabeled data have become an important component in statistical research. Despite interest, researchers investigated extensions. This paper introduces novel solution for learning sparse features context estimation: (s2net), which extends method, general mathematical formulation covers, but not limited to, regression classification problems. addition, flexible fast implementation s2net provided. advantages are illustrated different experiments using real synthetic sets. They show how improves performance other techniques been proposed learning.