Coedge: Cooperative dnn inference with adaptive workload partitioning over heterogeneous edge devices
Recent advances in artificial intelligence have driven increasing intelligent applications at
the network edge, such as smart home, smart factory, and smart city. To deploy …
the network edge, such as smart home, smart factory, and smart city. To deploy …
Quadralib: A performant quadratic neural network library for architecture optimization and design exploration
The significant success of Deep Neural Networks (DNNs) is highly promoted by the multiple
sophisticated DNN libraries. On the contrary, although some work have proved that …
sophisticated DNN libraries. On the contrary, although some work have proved that …
Dynamic-ofa: Runtime dnn architecture switching for performance scaling on heterogeneous embedded platforms
Mobile and embedded platforms are increasingly required to efficiently execute
computationally demanding DNNs across heterogeneous processing elements. At runtime …
computationally demanding DNNs across heterogeneous processing elements. At runtime …
Real-time object detection system with multi-path neural networks
Thanks to the recent advances in Deep Neural Networks (DNNs), DNN-based object
detection systems become highly accurate and widely used in real-time environments such …
detection systems become highly accurate and widely used in real-time environments such …
Accelerating split federated learning over wireless communication networks
The development of artificial intelligence (AI) provides opportunities for the promotion of
deep neural network (DNN)-based applications. However, the large amount of parameters …
deep neural network (DNN)-based applications. However, the large amount of parameters …
Content-aware network traffic prediction framework for quality of service-aware dynamic network resource management
Next-generation mobile networks, such as Fifth-Generation (5G), and Sixth-Generation (6G)
are envisioned to undergo an unprecedented transformation from connected things to …
are envisioned to undergo an unprecedented transformation from connected things to …
NeuLens: spatial-based dynamic acceleration of convolutional neural networks on edge
Convolutional neural networks (CNNs) play an important role in today's mobile and edge
computing systems for vision-based tasks like object classification and detection. However …
computing systems for vision-based tasks like object classification and detection. However …
[HTML][HTML] Multi‐objective evolutionary optimization for hardware‐aware neural network pruning
Neural network pruning is a popular approach to reducing the computational complexity of
deep neural networks. In recent years, as growing evidence shows that conventional …
deep neural networks. In recent years, as growing evidence shows that conventional …
Synergistically exploiting cnn pruning and hls versioning for adaptive inference on multi-fpgas at the edge
FPGAs, because of their energy efficiency, reconfigurability, and easily tunable HLS
designs, have been used to accelerate an increasing number of machine learning …
designs, have been used to accelerate an increasing number of machine learning …
Adaflow: A framework for adaptive dataflow CNN acceleration on fpgas
To meet latency and privacy requirements, resource-hungry deep learning applications
have been migrating to the Edge, where IoT devices can offload the inference processing to …
have been migrating to the Edge, where IoT devices can offload the inference processing to …