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

TitleTowards a Standard-based Domain-specific Platform to Solve Machine Learning-based Problems
Publication TypeJournal Article
Year of Publication2015
AuthorsGarcía-Díaz, V., J. Pascual-Espada, C. Pelayo G-Bustelo, and J. M. Cueva-Lovelle
JournalInternational Journal of Interactive Multimedia and Artificial Intelligence
IssueRegular Issue
Date Published12/2015

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.

KeywordsArtificial Intelligence, DSL, Machine Learning, MDE, Xtext
ijimai20153_5_1.pdf792.16 KB