Towards a Standard-based Domain-specific Platform to Solve Machine Learning-based Problems
- Vicente García Díaz
- Pascual Espada, Jordán
- Pelayo García Bustelo, Begoña Cristina
- Cueva Lovelle, Juan Manuel
ISSN: 1989-1660
Año de publicación: 2015
Volumen: 3
Número: 5
Páginas: 6-12
Tipo: Artículo
Otras publicaciones en: IJIMAI
Resumen
Machine 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.