This special issue of Neurocomputing presents N original articles, which are extended versions of selected papers from the 21 European Symposium on Artificial Neural Networks (ESANN). ESANN is a single-track conference held annually in Bruges, Belgium, one of the most beautiful medieval towns in Europe, whose atmosphere favours efficient work as well as enjoyable cultural activities (Bruges is a UNESCO World Heritage site). ESANN is organized by Prof. Michel Verleysen from Universite Catholique de Louvain, Belgium. The conference hosts a series of regular sessions about classification, clustering, recurrent networks, regression and forecasting, dimensionality reduction and feature selection, control and optimisation, etc. In addition, ESANN also welcomed in 2013 a few special sessions focused on more particular topics like processing and analysis of hyperspectral data, machine learning for multimedia applications, developments in kernel design, human activity and motion disorder recognition (towards smarter interactive cognitive environments, and sparsity for interpretation and visualisation in inference models. The contributions in this special issue show that ESANN covers a broad range of topics in neural computation, machine learning, and neuroscience from theoretical aspects to state-of-the-art applications and many related themes in signal processing and computational intelligence. About 130 researcher from more than 15 countries participated in the 21 ESANN in April, 2013. They presented 99 contributions, out of 125 submissions, and enjoyed the especially communicative atmosphere in Bruges. Based on the recommendations of specialsession organizers, the reviews of the conference papers, and the quality of the presentations made at the conference, a number of authors were invited to submit an extended version of their conference paper for this special issue of Neurocomputing. All of these articles were thoroughly reviewed once more by at least two independent experts and, finally the N articles presented in this volume were accepted for publication. In this special issue we can find a multitude of examples using neuro-computing and related techniques in different branches of research. The paper Correlation-based embedding of pairwise score data by Strickert,