01734nas a2200253   4500000000100000000000100001008004100002260001200043653000800055653000800063653002800071653002100099653001000120100003000130700002600160700003000186700002700216245009500243856009800338300000900436490000600445520101500451022001401466       2015                            d  c12/201510aMDE10aDSL10aArtificial Intelligence10aMachine Learning10aXtext1 aJuan Manuel Cueva-Lovelle1 aVicente García-Díaz1 aCristina Pelayo G-Bustelo1 aJordán Pascual-Espada00aTowards a Standard-based Domain-specific Platform to Solve Machine Learning-based Problems  uhttp://www.ijimai.org/journal/sites/default/files/files/2015/11/ijimai20153_5_1_pdf_15294.pdf  a6-120 v33 aMachine learning is one of the most important subfields of computer science and can be used to solve a variety of interesting artificial intelligence problems. There are different languages, framework and tools to define the data needed to solve machine learning-based problems. However, there is a great number of very diverse alternatives which makes it difficult the intercommunication, portability and re-usability of the definitions, designs or algorithms that any developer may create. In this paper, we take the first step towards a language and a development environment independent of the underlying technologies, allowing developers to design solutions to solve machine learning-based problems in a simple and fast way, automatically generating code for other technologies. That can be considered a transparent bridge among current technologies. We rely on Model-Driven Engineering approach, focusing on the creation of models to abstract the definition of artifacts from the underlying technologies.  a1989-1660