[EN] Most previous longitudinal studies of functional magnetic resonance imaging (fMRI) in first-episode psychosis (FEP) using cognitive paradigm task found an increased activation after antipsychotic medications. We ...

[EN] Recent improvements in deep learning techniques show that deep models can extract more meaningful data directly from raw signals than conventional parametrization techniques, making it possible to avoid specific feature ...

This paper proposes the use of hybrid Hidden Markov Model (HMM)/Artificial Neural Network (ANN) models for recognizing unconstrained offline handwritten texts. The structural part of the optical models has been modeled ...

[EN] The assessment of the learning experience of Massive Open Online Courses (MOOCs) at Universitat Polit`ecnica de Val`encia (UPV) is currently performed through a questionnaire which only evaluates the pedagogical ...

[EN] Unconstrained off-line continuous handwritten text recognition is a very challenging task which has been recently addressed by different promising techniques. This work presents our latest contribution to this task, ...

Nowadays, the main libraries and document archives are investing a considerable effort on digitizing their collections. Indeed, most of them are scanning the documents and publishing the resulting images without their ...

[ES] La comunicación mediante el habla permite a los individuos transmitir no sólo información lingüística, sino también su estado emocional, de forma eficaz y natural. El reconocimiento automático del estado emocional de ...

[EN] A novel method for finding linear mappings among word embeddings for several languages, taking as pivot a shared, multilingual embedding space, is proposed in this paper. Previous approaches learned translation matrices ...