… at running complex deep learning pipelines on mobile devices. In this paper, we focused
on reducing the power consumption of executing deep learning pipeline on a mobile device …

… We propose a new algorithm based on deep learning, which has been widely used in various
fields due to its potential. Especially, many studies have demonstrated that deep learning …

… deep learning structures. Our system is able to detect unauthorized usage while allowing the
device’s owner to safely access the device. … to traditional machine learning techniques. Our …

… Finally, considering the computing environment and data characteristics of mobile devices,
we propose a lightweight network structure for optical character recognition (OCR) on …

… in deep learning to mobile sensing from the cloud toward the edge and/or mobile devices.
However, … overhead associated with deep learning, training models requiring large data sets, …

… of mobile devices and deep learning, mobile smart applications using deep learning …
may hold for deploying deep learning applications on mobile devices research, which may …

… To further analyze the accuracy degradation of these deep learning models, we present the
worst-case localization error for the two deep learning models in Figure 8. We can observe …

… in deep learning and mobile devices. In contrast, DXTK aims to allow any developer to use
deep learning … usage to levels that are feasible for mobile and embedded devices. Further, …

… , deep learning approaches are at the forefront of so many domains. Deep learning models
… Running those models on the mobile devices require hardware-aware optimizations and in …

… In contrast, faults related to the deployment of DL models on mobile devices (named … of
DL models on mobile devices (named as deployment faults of mobile DL apps) should be …