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

Author
Keywords
Abstract
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.
Year of Publication
2015
Journal
International Journal of Interactive Multimedia and Artificial Intelligence
Volume
3
Issue
Regular Issue
Number
5
Number of Pages
6-12
Date Published
12/2015
ISSN Number
1989-1660
Citation Key
URL
http://www.ijimai.org/journal/sites/default/files/files/2015/11/ijimai20153_5_1_pdf_15294.pdf
DOI
10.9781/ijimai.2015.351
Attachment