Autonomic machine learning for intelligent databases

초록

Various machine learning algorithms are available off the shelf, even for free. It takes an expert to choose a proper algorithm for given task and to set hyperparameters of the algorithm. This paper addresses an architecture of autonomic machine learning platform with which developers get some assistance in choosing a machine learning algorithm appropriate to a task and in selecting the values of hyperparameters of the algorithm. Due to massive computation demands on executing machine learning algorithms, the platform is designed to utilize the external computing resources such as cloud computing systems and distributed computing systems. This paper presents the design choices and architecture of the proposed platform, and a possible application to intelligent databases. ? Springer International Publishing AG, part of Springer Nature 2019.