E Li, L Zeng, Z Zhou, X Chen - IEEE Transactions on Wireless …, 2019 - ieeexplore.ieee.org
As a key technology of enabling Artificial Intelligence (AI) applications in 5G era, Deep Neural Networks (DNNs) have quickly attracted widespread attention. However, it is …
C Li, H Xu, Y Xu, Z Wang, L Huang - … WASA 2021, Nanjing, China, June 25 …, 2021 - Springer
Recently, deep neural networks (DNNs) have been applied to most intelligent applications and deployed on different kinds of devices. However, DNN inference is resource-intensive …
E Li, Z Zhou, X Chen - Proceedings of the 2018 workshop on mobile …, 2018 - dl.acm.org
As the backbone technology of machine learning, deep neural networks (DNNs) have have quickly ascended to the spotlight. Running DNNs on resource-constrained mobile devices …
S Hu, C Dong, W Wen - 2021 IEEE 6th International …, 2021 - ieeexplore.ieee.org
Deep Neural Network (DNN) based artificial intelligence help driving the great development of mobile Internet. However, the hardware of a mobile device may not be sufficiently to meet …
Abstract Deep Neural Networks (DNNs) based on intelligent applications have been intensively deployed on mobile devices. Unfortunately, resource-constrained mobile devices …
C Hu, Y Bai, R Wang, C Liu… - 2020 IEEE 22nd …, 2020 - ieeexplore.ieee.org
Recently, deep learning technology has shined in the fields of computer vision, natural language processing and speech recognition, and related products have sprung up like …
Z Huang, F Dong, D Shen, J Zhang… - 2021 IEEE 41st …, 2021 - ieeexplore.ieee.org
In recent years, deep neural networks (DNNs) have witnessed a booming of artificial intelligence Internet of Things applications with stringent demands across high accuracy and …
Mobile Edge Computing (MEC) has emerged as a promising paradigm catering to overwhelming explosions of mobile applications, by offloading the compute-intensive tasks …
C Xiao, D Xu, S Qiu, C Shi… - … IEEE Intl Conf on Parallel & …, 2021 - ieeexplore.ieee.org
Depthwise Separable Convolution can effectively reduce parameters and operations with little loss in precision, which becomes more and more popular in many innovative neural …