Improved Machine Learning using Confidence

Wearable gadgets are in for an exponential rise thanks to the improvements in the silicon scaling and ubiquity of Internet as well as battery technology and sensor amelioration. However, despite these advances, wearable gadgets remain resource constrained devices requiring further improvements in all those areas. Self-awareness enables a system to adjust its behaviors to enhance the operations of the system and meet its goals. In this paper, we review one of the self-awareness techniques used in wearable devices and machine learning, namely confidence, which leads to their improvements. In particular, we focus on how confidence helps to maintain or enhance performance of machine learning techniques while reducing the complexity of the processes and required resources for running them on resource constrained devices. We look into three examples, epilepsy monitoring, iris flower detection, and image classification.