Related papers: LiveWN, cpu scavenging in the Grid Era

In this paper we present an approach for training deep generative models solely based on solving determined systems of linear equations. A network that uses this approach, called a StarNet, has the following desirable properties: 1)…

In this paper we present Simgrid, a toolkit for the versatile simulation of large scale distributed systems, whose development effort has been sustained for the last fifteen years. Over this time period SimGrid has evolved from a…

Dynamic neural networks (DyNNs) have become viable techniques to enable intelligence on resource-constrained edge devices while maintaining computational efficiency. In many cases, the implementation of DyNNs can be sub-optimal due to its…

This work addresses the problem of exploration in an unknown environment. For linear dynamical systems, we use an experimental design framework and introduce an online greedy policy where the control maximizes the information of the next…

The Grid technologies are in ongoing development. Using current Grid toolkits like the Globus toolkit gives one the possibility to build up virtual organizations. Although these tookits are in still under development and do not feature all…

Learning-based methods for synthesizing controllers have gained popularity due to their high expressiveness and strong empirical performance. However, in safety-critical scenarios such as autonomous driving, robotics, and power systems,…

With the ongoing emergence of smart and distributed grids, it becomes increasingly important to understand as well as improve legacy infrastructure while operating a much more interconnected and fragile architecture. To support this…

Geometry is a ubiquitous tool in computer graphics, design, and engineering. However, the lack of large shape datasets limits the application of state-of-the-art supervised learning methods and motivates the exploration of alternative…

The advent of 6G wireless communication marks a transformative era in technological connectivity, bringing forth challenges and opportunities alike. This paper unveils an innovative, open-source simulator, meticulously crafted for cell-free…

Living lab outdoor experimentation using pervasive computing provides new opportunities: higher realism, external validity and socio-spatio-temporal observations in large scale. However, experimentation `in the wild' is complex and costly.…

Inspired by the principles of speed reading, we introduce Skim-RNN, a recurrent neural network (RNN) that dynamically decides to update only a small fraction of the hidden state for relatively unimportant input tokens. Skim-RNN gives…

Machine learning has shown growing success in recent years. However, current machine learning systems are highly specialized, trained for particular problems or domains, and typically on a single narrow dataset. Human learning, on the other…

The main objective of this paper is to design and develop an automatic vehicle, fully controlled by a computer system. The vehicle designed in the present work can move in a pre-determined path and work automatically without the need of any…

Dynamic spectrum access systems typically require information about the spectrum occupancy and thus the presence of other users in order to make a spectrum al-location decision for a new device. Simple methods of spectrum occupancy…

Next generation networks are envisioned to have ubiquitous availability and seamless access as main goals. In general, coexistence of multiple access technologies is one of the most promising way to achieve these goals, particularly using…

In order to better accommodate the dramatically increasing demand for data caching and computing services, storage and computation capabilities should be endowed to some of the intermediate nodes within the network. In this paper, we design…

Designing a lightweight semantic segmentation network often requires researchers to find a trade-off between performance and speed, which is always empirical due to the limited interpretability of neural networks. In order to release…

To reduce user costs and maximize cluster utilization, large model training increasingly leverages volatile but inexpensive GPU capacity, such as spot instances and reclaimable resources in shared clusters. Yet, capitalizing on these…

Smart grids are crucial for meeting rising energy demands driven by global population growth and urbanization. By integrating renewable energy sources, they enhance efficiency, reliability, and sustainability. However, ensuring their…

As deep learning models become popular, there is a lot of need for deploying them to diverse device environments. Because it is costly to develop and optimize a neural network for every single environment, there is a line of research to…