Related papers: LCDN: Providing Network Determinism with Low-Cost …

One of the most recent architectures of networks is Software-Defined Networks (SDNs) using a con- troller appliance to control the set of switches on the network. The controlling process includes installing or uninstalling packet-processing…

As deep neural networks continue to expand and become more complex, most edge devices are unable to handle their extensive processing requirements. Therefore, the concept of distributed inference is essential to distribute the neural…

As the share of Distributed energy resources (DER) in the low voltage distribution network (DN) is expected to rise, a higher and more variable electric load and generation could stress the DNs, leading to increased congestion and power…

In the past decade, convolutional neural networks (CNNs) have shown prominence for semantic segmentation. Although CNN models have very impressive performance, the ability to capture global representation is still insufficient, which…

A novel convolution neural network model, abbreviated NL-CNN is proposed, where nonlinear convolution is emulated in a cascade of convolution + nonlinearity layers. The code for its implementation and some trained models are made publicly…

We focus on C-RAN random access protocols for IoT devices that yield low-latency high-rate active-device detection in dense networks of large-array remote radio heads. In this context, we study the problem of learning the strengths of links…

Stochastic Processing Networks (SPNs) can be used to model communication networks, manufacturing systems, service systems, etc. We consider a real-time SPN where tasks generate jobs with strict deadlines according to their traffic patterns.…

Low precision deep neural network (DNN) training is one of the most effective techniques for boosting DNNs' training efficiency, as it trims down the training cost from the finest bit level. While existing works mostly fix the model…

Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…

Modern deep neural networks (DNNs) have greatly facilitated the development of sequential recommender systems by achieving state-of-the-art recommendation performance on various sequential recommendation tasks. Given a sequence of…

Supporting Ultra-Reliable Low-Latency Communication (URLLC) in the Internet of Things (IoT) era is challenging due to stringent constraints on latency and reliability combined with the simple circuitry of IoT nodes. Diversity is usually…

With the development of 5G, innovative applications requiring bounded transmission delays and zero packet loss emerge, e.g., AR, industrial automation, and smart grid. In this circumstance, time-sensitive networking (TSN) is proposed, which…

We present Linear Diffusion Networks (LDNs), a novel architecture that reinterprets sequential data processing as a unified diffusion process. Our model integrates adaptive diffusion modules with localized nonlinear updates and a…

Several recently proposed techniques achieve latency reduction by trading it off for some amount of additional bandwidth usage. But how would one quantify whether the tradeoff is actually beneficial in a given system? We develop an economic…

Semantic grids can be useful representations of the scene around an autonomous system. By having information about the layout of the space around itself, a robot can leverage this type of representation for crucial tasks such as navigation…

The emerging paradigm of resource disaggregation enables the deployment of cloud-like services across a pool of physical and virtualized resources, interconnected using a network fabric. This design embodies several benefits in terms of…

NCs are the natural evolution of PCs, ubiquitous computers everywhere. The current vision of NCs requires two improbable developments: (1) inexpensive high-bandwidth WAN links to the Internet, and (2) inexpensive centralized servers. The…

When deploying deep learning models to a device, it is traditionally assumed that available computational resources (compute, memory, and power) remain static. However, real-world computing systems do not always provide stable resource…

This paper deals with congestion control in a software defined network (SDN) setting. Presently, explicit router schemes, such as Explicit Congestion Notification (ECN), work in conjunction with the TCP protocol to handle congestion in a…

Deep Neural Networks (DNNs) have shown excellent performance in a wide range of machine learning applications. Knowing the latency of running a DNN model or tensor program on a specific device is useful in various tasks, such as DNN graph-…