Deep learning (DL) has demonstrated great performance in various applications on
powerful computers and servers. Recently, with the advancement of more powerful mobile …

Computing at the edge is important in remote settings, however, conventional hardware is
not optimized for utilizing deep neural networks. The Google Edge TPU is an emerging …

Developing efficient on-the-edge Deep Learning (DL) applications is a challenging and non-
trivial task, as first different DL models need to be explored with different trade-offs between …

In this paper, we propose TECO, a multi-dimensional pruning framework to collaboratively
prune the three dimensions (depth, width, and resolution) of convolutional neural networks …

Autonomous Vehicles (AVs) redefine transportation with sophisticated technology,
integrating sensors, cameras, and intricate algorithms. Implementing machine learning in AV …

Hardware accelerators such as GPUs are required for real-time, low latency inference with
Deep Neural Networks (DNN). Providing inference services in the cloud can be resource …

Several manufacturers sell specialized USB devices for accelerating machine learning (ML)
on the edge. While being generally promoted as a versatile solution for more efficient edge …

Analyzing and modeling the performance and energy consumption of hybrid Edge
Computing systems with embedded devices and Artificial Intelligence (AI) accelerators is …

On Hardware-Aware Design and Optimization of Edge Intelligence Page 1 On Hardware-Aware
Design and Optimization of Edge Intelligence Shuo Huai∗†, Hao Kong∗†, Xiangzhong Luo∗ …

Due to the development in various tools and deep learning (DL) techniques that might be
helpful in evaluating Internet of Things (IoT) big data, the integration of the IoT with DL has …