An adaptive semi-supervised ensemble method, ASSEMBLE, is proposed that constructs classification ensembles based on both labeled and unlabeled data. ASSEMBLE alternates between a...
Multi-class classification schemes typically require human input in the form of precise category names or numbers for each example to be annotated – providing this can be impra...
Ajay Joshi, Fatih Porikli, Nikolaos Papanikolopoul...
Abstract—This paper presents a novel study on how to distribute neural networks in a wireless sensor networks (WSNs) such that the energy consumption is minimized while improving...
Recently, significant progress has been made on learning structured predictors via coordinated training algorithms such as conditional random fields and maximum margin Markov ne...
We present a novel algorithm for multilingual dependency parsing that uses annotations from a diverse set of source languages to parse a new unannotated language. Our motivation i...