Towards a Standard-based Domain-specific Platform to Solve Machine Learning-based Problems

• Autores: Vicente García Díaz, Jordán Pascual Espada, Begoña Cristina Pelayo García Bustelo, Juan Manuel Cueva Lovelle
• Localización: IJIMAI, ISSN-e 1989-1660, Vol. 3, Nº. 5, 2015, págs. 6-12
• Idioma: inglés
• Enlaces
  • Texto completo (pdf)
• Dialnet Métricas: 1 Cita
• 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.