Related papers: Distributed or Monolithic? A Computational Archite…

Driven by the vision of ubiquitous connectivity and wireless intelligence, the evolution of ultra-dense constellation-based satellite-integrated Internet is underway, now taking preliminary shape. Nevertheless, the entrenched institutional…

The distributed computing is done on many systems to solve a large scale problem. The growing of high-speed broadband networks in developed and developing countries, the continual increase in computing power, and the rapid growth of the…

This paper proposes a novel three tier architecture for federated learning to optimize edge computing environments. The proposed architecture addresses the challenges associated with client data heterogeneity and computational constraints.…

As deep learning applications continue to become more diverse, an interesting question arises: Can general problem solving arise from jointly learning several such diverse tasks? To approach this question, deep multi-task learning is…

Being a very promising technology, with impressive advances in the recent years, it is still unclear how quantum computing will scale to satisfy the requirements of its most powerful applications. Although continued progress in the…

In this paper, we present a unified framework for decision making under uncertainty. Our framework is based on the composite of two risk measures, where the inner risk measure accounts for the risk of decision given the exact distribution…

If learning methods are to scale to the massive sizes of modern datasets, it is essential for the field of machine learning to embrace parallel and distributed computing. Inspired by the recent development of matrix factorization methods…

Ensembles of neural networks achieve superior performance compared to stand-alone networks in terms of accuracy, uncertainty calibration and robustness to dataset shift. \emph{Deep ensembles}, a state-of-the-art method for uncertainty…

Monolithic neural networks that make use of a single set of weights to learn useful representations for downstream tasks explicitly dismiss the compositional nature of data generation processes. This characteristic exists in data where…

Recent progress in time-series forecasting has led to rapidly increasing architectural complexity, yet many reported State-of-the-Art gains are statistically fragile or misattributed. We argue that progress requires a shift from model…

A large body of research in continual learning is devoted to overcoming the catastrophic forgetting of neural networks by designing new algorithms that are robust to the distribution shifts. However, the majority of these works are strictly…

The evolution of computer architecture has led to a paradigm shift from traditional single-core processors to multi-core and domain-specific architectures that address the increasing demands of modern computational workloads. This paper…

In this paper we describe an architecture which: Permits the deployment and execution of components in appropriate geographical locations. Provides security mechanisms that prevent misuse of the architecture. Supports a programming model…

Commercially impactful quantum algorithms such as quantum chemistry and Shor's algorithm require a number of qubits and gates far beyond the capacity of any existing quantum processor. Distributed architectures, which scale horizontally by…

The design of neural network architectures is frequently either based on human expertise using trial/error and empirical feedback or tackled via large scale reinforcement learning strategies performed over distinct discrete architecture…

Emerging cyber-physical systems incorporate systems of systems that have functional interdependencies. With the increase in complexity of the cyber-physical systems, the attack surface also expands, making cyber-physical systems more…

Distribution can be a feature of the software evolution process. In other words, temporally and spatially distributed teams and organizations can develop and work on a software application. The simplest case is to outsource production and…

3D promises a new dimension in composing systems by aggregating chips. Literally. While the most common uses are still tightly connected with its early forms as a packaging technology, new application domains have been emerging. As the…

Engineering system design, viewed as a decision-making process, faces challenges due to complexity and uncertainty. In this paper, we present a framework proposing the use of the Deep Q-learning algorithm to optimize the design of…

Large scale systems are forecasted to greatly impact our future lives thanks to their wide ranging applications including cooperative robotics, mobility on demand, resource allocation, supply chain management. While technological…