TY - JOUR
KW - MDE
KW - DSL
KW - Artificial Intelligence
KW - Machine Learning
KW - Xtext
AU - Juan Manuel Cueva-Lovelle
AU - Vicente García-Díaz
AU - Cristina Pelayo G-Bustelo
AU - Jordán Pascual-Espada
AB - 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.
IS - Regular Issue
M1 - 5
N2 - 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.
PY - 2015
SP - 6
EP - 12
T2 - International Journal of Interactive Multimedia and Artificial Intelligence
TI - Towards a Standard-based Domain-specific Platform to Solve Machine Learning-based Problems
UR - http://www.ijimai.org/journal/sites/default/files/files/2015/11/ijimai20153_5_1_pdf_15294.pdf
VL - 3
SN - 1989-1660
ER -