With the rapid development of mobile devices and deep learning, mobile smart applications using deep learning technology have sprung up. It satisfies multiple needs of users, network operators and service providers, and rapidly becomes a main research focus. In recent years, deep learning has achieved tremendous success in image processing, natural language processing, language analysis and other research fields. Despite the task performance has been greatly improved, the resources required to run these models have increased significantly. This poses a major challenge for deploying such applications on resource-restricted mobile devices. Mobile intelligence needs faster mobile processors, more storage space, smaller but more accurate models, and even the assistance of other network nodes. To help the readers establish a global concept of the entire research direction concisely, we classify the latest works in this field into two categories, which are local optimization on mobile devices and distributed optimization based on the computational position of machine learning tasks. We also list a few typical scenarios to make readers realize the importance and indispensability of mobile deep learning applications. Finally, we conjecture what the future may hold for deploying deep learning applications on mobile devices research, which may help to stimulate new ideas. 相似文献
Due to the complexity of blockchain technology, it usually costs too much effort to build, maintain and monitor a blockchain system that supports a targeted application. To this end, the emerging “Blockchain as a Service” (BaaS) makes the blockchain and distributed ledgers more accessible, particularly for businesses, by reducing costs and overheads. BaaS combines the high computing power of cloud computing, the pervasiveness of IoT and the decentralization of blockchain, allowing people to build their own applications while ensuring the transparency and openness of the system. This paper surveys the research outputs of both academia and industry. First, it introduces the representative architectures of BaaS systems and then summarizes the research contributions of BaaS from the technologies for service provision, roles, container and virtualization, interfaces, customization and evaluation. The typical applications of BaaS in both academic and practical domains are also introduced. At present, the research on the blockchain is abundant, but research on BaaS is still in its infancy. Six challenges of BaaS are concluded in this paper for further study directions. 相似文献
Mobile Networks and Applications - In order to improve the ability of quantitative evaluation of e-commerce advertising click rate, a model of e-commerce advertising click rate evaluation based on... 相似文献
The Journal of Supercomputing - In the edge computing, service placement refers to the process of installing service platforms, databases, and configuration files corresponding to computing tasks... 相似文献
The heavy reliance on data is one of the major reasons that currently limit the development of deep learning. Data quality directly dominates the effect of deep learning models, and the long-tailed distribution is one of the factors affecting data quality. The long-tailed phenomenon is prevalent due to the prevalence of power law in nature. In this case, the performance of deep learning models is often dominated by the head classes while the learning of the tail classes is severely underdeveloped. In order to learn adequately for all classes, many researchers have studied and preliminarily addressed the long-tailed problem. In this survey, we focus on the problems caused by long-tailed data distribution, sort out the representative long-tailed visual recognition datasets and summarize some mainstream long-tailed studies. Specifically, we summarize these studies into ten categories from the perspective of representation learning, and outline the highlights and limitations of each category. Besides, we have studied four quantitative metrics for evaluating the imbalance, and suggest using the Gini coefficient to evaluate the long-tailedness of a dataset. Based on the Gini coefficient, we quantitatively study 20 widely-used and large-scale visual datasets proposed in the last decade, and find that the long-tailed phenomenon is widespread and has not been fully studied. Finally, we provide several future directions for the development of long-tailed learning to provide more ideas for readers.