Web-based Automatic Deep Learning Service Generation System by Ontology Technologies

Abstract

Although deep learning (DL) has obtained great achievements in the industry, the involvement of artificial intelligence (AI) experts in developing customized DL services raises high costs and hinders its wide application in the business domain. In this research, a Web-based automatic DL service generation system is presented to address the problem. The system can generate customized DL services without involving AI experts. The main principle of the system adopts ontology technologies to organize DL domain knowledge and generate target services based on the user's requests posted from the front-end web page. In the empirical study, the whole scenario of the system is demonstrated, and the scalability is also evaluated. The result shows that our system can generate customized services correctly and has good scalability.