Related papers: A Hierarchical Dataflow-Driven Heterogeneous Archi…
Optical wireless communication (OWC) is a promising technology that can provide high data rates while supporting multiple users. The Optical Wireless (OW) physical layer has been researched extensively, however less work was devoted to…
To achieve high rate of Multi-Giga-bits-per-second for multimedia applications at personal area level, 60 GHz communication technologies are most potential candidates. Due to some special characteristics of 60 GHz band of frequencies and…
Transformers have revolutionized AI in natural language processing and computer vision, but their large computation and memory demands pose major challenges for hardware acceleration. In practice, end-to-end throughput is often limited by…
In this paper, we propose a systematic solution to the problem of scheduling delay-sensitive media data for transmission over time-varying wireless channels. We first formulate the dynamic scheduling problem as a Markov decision process…
Computer vision on low-power edge devices enables applications including search-and-rescue and security. State-of-the-art computer vision algorithms, such as Deep Neural Networks (DNNs), are too large for inference on low-power edge…
Deploying deep neural networks (DNNs) across homogeneous edge devices (the devices with the same SKU labeled by the manufacturer) often assumes identical performance among them. However, once a device model is widely deployed, the…
Distributed synchronous stochastic gradient descent has been widely used to train deep neural networks (DNNs) on computer clusters. With the increase of computational power, network communications generally limit the system scalability.…
The paper presents two mechanisms for designing an on-demand, reliable and efficient collection protocol for Wireless Sensor Networks. The former is the Bidirectional Link Quality Estimation, which allows nodes to easily and quickly compute…
Signal processing is crucial for satisfying the high data rate requirements of future sixth-generation (6G) wireless networks. However, the rapid growth of wireless networks has brought about massive data traffic, which hinders the…
This paper addresses the problem of averaging numbers across a wireless network from an important, but largely neglected, viewpoint: bandwidth/energy efficiency. We show that existing distributed averaging schemes have several drawbacks and…
In this paper, we investigate high-altitude platform station (HAPS) wireless networks for simultaneous non-orthogonal unicast and multicast transmissions. Specifically, stacked intelligent metasurface (SIM)-based wave-domain beamforming is…
In wireless ad hoc networks, distributed nodes can collaboratively form an antenna array for long-distance communications to achieve high energy efficiency. In recent work, Ochiai, et al., have shown that such collaborative beamforming can…
Caching the popular multimedia content is a promising way to unleash the ultimate potential of wireless networks. In this paper, we contribute to proposing and analyzing the cache-based content delivery in a three-tier heterogeneous network…
Data-driven approaches and paradigms have become promising solutions to efficient network performances through optimization. These approaches focus on state-of-the-art machine learning techniques that can address the needs of 5G networks…
Future wireless networks will progressively displace service provisioning towards the edge to accommodate increasing growth in traffic. This paradigm shift calls for smart policies to efficiently share network resources and ensure service…
Future wireless networks are required to support 1000 times higher data rate, than the current LTE standard. In order to meet the ever increasing demand, it is inevitable that, future wireless networks will have to develop seamless…
Tensor processing units (TPUs) are one of the most well-known machine learning (ML) accelerators utilized at large scale in data centers as well as in tiny ML applications. TPUs offer several improvements and advantages over conventional ML…
Heterogeneous nodes that combine multi-core CPUs with diverse accelerators are rapidly becoming the norm in both high-performance computing (HPC) and AI infrastructures. Exploiting these platforms, however, requires orchestrating several…
Modern Graphics Processing Units (GPUs) are well provisioned to support the concurrent execution of thousands of threads. Unfortunately, different bottlenecks during execution and heterogeneous application requirements create imbalances in…
In this position paper we argue for standardizing how we share and process data in scientific workflows at the network-level to maximize step re-use and workflow portability across platforms and networks in pursuit of a foundational…