IEEE access special section editorial: Machine learning designs, implementations and techniques

Abstract

Most modern machine learning research is devoted to improving the accuracy of prediction. However, less attention is paid to the deployment of the machine and deep learning systems, supervised/unsupervised techniques for mining healthcare data, and time series similarity and irregular temporal data analysis [item 1)–9) in the Appendix]. Most deployments are in the cloud, with abundant and scalable resources, and a free choice of computation platform. However, with the advent of intelligent physical devices—such as intelligent robots or self-driven cars—resources are more limited, and the latency may be strictly bounded [item 1)–9) in the Appendix].