Related papers: Enhancing Split Computing and Early Exit Applicati…

Sparsity helps reduce the computational complexity of deep neural networks by skipping zeros. Taking advantage of sparsity is listed as a high priority in next generation DNN accelerators such as TPU. The structure of sparsity, i.e., the…

Running multiple deep neural networks (DNNs) in parallel has become an emerging workload in both edge devices, such as mobile phones where multiple tasks serve a single user for daily activities, and data centers, where various requests are…

Recent years have witnessed increasing interest in machine learning inferences on serverless computing for its auto-scaling and cost effective properties. Existing serverless computing, however, lacks effective job scheduling methods to…

The rapid development of artificial intelligence together with the powerful computation capabilities of the advanced edge servers make it possible to deploy learning tasks at the wireless network edge, which is dubbed as edge intelligence…

Recently, deep neural networks have been outperforming conventional machine learning algorithms in many computer vision-related tasks. However, it is not computationally acceptable to implement these models on mobile and IoT devices and the…

This paper proposes a neural architecture search (NAS) method for split computing. Split computing is an emerging machine-learning inference technique that addresses the privacy and latency challenges of deploying deep learning in IoT…

Gigantic pre-trained models have become central to natural language processing (NLP), serving as the starting point for fine-tuning towards a range of downstream tasks. However, two pain points persist for this paradigm: (a) as the…

The growing energy and performance costs of deep learning have driven the community to reduce the size of neural networks by selectively pruning components. Similarly to their biological counterparts, sparse networks generalize just as…

By adding exiting layers to the deep learning networks, early exit can terminate the inference earlier with accurate results. The passive decision-making of whether to exit or continue the next layer has to go through every pre-placed…

The number of processing elements (PEs) in a fixed-sized systolic accelerator is well matched for large and compute-bound DNNs; whereas, memory-bound DNNs suffer from PE underutilization and fail to achieve peak performance and energy…

The success of deep neural networks (DNNs) is heavily dependent on computational resources. While DNNs are often employed on cloud servers, there is a growing need to operate DNNs on edge devices. Edge devices are typically limited in their…

We focus on computation offloading of applications based on convolutional neural network (CNN) from moving devices, such as mobile robots or autonomous vehicles, to MultiAccess Edge Computing (MEC) servers via a mobile network. In order to…

Deep neural networks (DNNs) have been successfully applied in various fields. In DNNs, a large number of multiply-accumulate (MAC) operations are required to be performed, posing critical challenges in applying them in resource-constrained…

Deep Neural Networks (DNNs) have grown increasingly large in size to achieve state of the art performance across a wide range of tasks. However, their high computational requirements make them less suitable for resource-constrained…

Deployment of dynamic neural networks on edge accelerators requires careful consideration of hardware constraints beyond conventional complexity metrics such as Multiply-Accumulate operations. In Early-Exiting Neural Networks (EENN), exit…

Deep Neural Networks (DNNs) are generally designed as sequentially cascaded differentiable blocks/layers with a prediction module connected only to its last layer. DNNs can be attached with prediction modules at multiple points along the…

The increasing pervasiveness of intelligent mobile applications requires to exploit the full range of resources offered by the mobile-edge-cloud network for the execution of inference tasks. However, due to the heterogeneity of such…

Partitioned DNN inference is a promising approach for latency-sensitive intelligent services in edge networks, since it allows different parts of a model to be executed across end devices, edge servers, and the cloud. However, in a…

Deep Neural Networks (DNNs) have been established as the state-of-the-art algorithm for advanced machine learning applications. Recently proposed by the Google Brain's team, the Capsule Networks (CapsNets) have improved the generalization…

The convergence of artificial intelligence and edge computing has spurred growing interest in enabling intelligent services directly on resource-constrained devices. While traditional deep learning models require significant computational…