Related papers: Nanosecond Precision Time Synchronization for Opti…
The rise of deep learning has led to various successful attempts to apply deep neural networks (DNNs) for important networking tasks such as intrusion detection. Yet, running DNNs in the network control plane, as typically done in existing…
Deep learning is able to functionally simulate the human brain and thus, it has attracted considerable interest. Optics-assisted deep learning is a promising approach to improve the forward-propagation speed and reduce the power…
Time series forecasting poses significant challenges in non-stationary environments where underlying patterns evolve over time. In this work, we propose a novel framework that enhances deep neural network (DNN) performance by leveraging…
Bulk synchronous parallel (BSP) is the de-facto paradigm for distributed DNN training in today's production clusters. However, due to the global synchronization nature, its performance can be significantly influenced by network bottlenecks…
The computational demands of modern AI have spurred interest in optical neural networks (ONNs) which offer the potential benefits of increased speed and lower power consumption. However, current ONNs face various challenges,most…
Processing visual data on mobile devices has many applications, e.g., emergency response and tracking. State-of-the-art computer vision techniques rely on large Deep Neural Networks (DNNs) that are usually too power-hungry to be deployed on…
In the global network of institutions engaged with the realization of International Atomic Time (TAI), atomic clocks and time scales are compared by means of the Global Positioning System (GPS) and by employing telecommunication satellites…
Accurate time synchronization is essential for Internet of Things (IoT) systems, where multiple distributed nodes must share a common time base for coordinated sensing and data fusion. However, conventional synchronization approaches suffer…
Data fusion algorithms that employ LiDAR measurements, such as Visual-LiDAR, LiDAR-Inertial, or Multiple LiDAR Odometry and simultaneous localization and mapping (SLAM) rely on precise timestamping schemes that grant synchronicity to data…
Accurate spatiotemporal alignment of multi-view video streams is essential for a wide range of dynamic-scene applications such as multi-view 3D reconstruction, pose estimation, and scene understanding. However, synchronizing multiple…
Data center networks (DCNs) are essential infrastructures to embrace the era of highly diversified massive amount of data generated by emerging technological applications. In order to store and process such a data deluge, today's DCNs have…
Emerging reconfigurable datacenters allow to dynamically adjust the network topology in a demand-aware manner. These datacenters rely on optical switches which can be reconfigured to provide direct connectivity between racks, in the form of…
Time synchronization of devices in Internet-of-Things (IoT) networks is one of the challenging problems and a pre-requisite for the design of low-latency applications. Although many existing solutions have tried to address this problem,…
One of the most important problems in the field of distributed optimization is the problem of minimizing a sum of local convex objective functions over a networked system. Most of the existing work in this area focus on developing…
Designing domain specific neural networks is a time-consuming, error-prone, and expensive task. Neural Architecture Search (NAS) exists to simplify domain-specific model development but there is a gap in the literature for time series…
Nanophotonics provides the ability to rapidly and precisely reconfigure light beams on a compact platform. Infrared nanophotonic devices are widely used in data communications to overcome traditional bandwidth limitations of electrical…
Optimal transmission switching (OTS) improves optimal power flow (OPF) by selectively opening transmission lines, but its mixed-integer formulation increases computational complexity, especially on large grids. To deal with this, we propose…
Leveraging the unrivaled performance of optical clocks in applications in fundamental physics beyond the standard model, in geo-sciences, and in astronomy requires comparing the frequency of distant optical clocks truthfully. Meeting this…
Synchronization in networks with delayed coupling are ubiquitous in nature and play a key role in almost all fields of science including physics, biology, ecology, climatology and sociology. In general, the published works on network…
Deep Neural Networks (DNNs) approaches for the Optimal Power Flow (OPF) problem received considerable attention recently. A key challenge of these approaches lies in ensuring the feasibility of the predicted solutions to physical system…