Related papers: Accelerator Real-time Edge AI for Distributed Syst…
Upon the significant performance of the supervised deep neural networks, conventional procedures of developing ML system are \textit{task-centric}, which aims to maximize the task accuracy. However, we scrutinized this \textit{task-centric}…
Multi-access edge computing (MEC) is viewed as an integral part of future wireless networks to support new applications with stringent service reliability and latency requirements. However, guaranteeing ultra-reliable and low-latency MEC…
Recent breakthroughs in artificial intelligence (AI), wireless communications, and sensing technologies have accelerated the evolution of edge intelligence. However, conventional systems still grapple with issues such as low communication…
ARES (Accelerator Research Experiment at SINBAD) is a linear accelerator at the SINBAD (Short INnovative Bunches and Accelerators at DESY) facility at DESY. ARES was designed to combine reproducible beams from conventional RF-based…
Advances in hybrid bonding and packaging have driven growing interest in 3D DRAM-stacked accelerators with higher memory bandwidth and capacity. As LLMs scale to hundreds of billions or trillions of parameters, distributed inference across…
Distributed real-time and embedded (DRE) systems executing mixed criticality task sets are increasingly being deployed in mobile and embedded cloud computing platforms, including space applications. These DRE systems must not only operate…
Over the past decade, Fermilab has focused efforts on the intensity frontier physics and is committed to increase the average beam power delivered to the neutrino and muon programs substantially. Many upgrades to the existing injector…
Machine learning (ML) can be used in various ways to improve multi-user multiple-input multiple-output (MU-MIMO) receive processing. Typical approaches either augment a single processing step, such as symbol detection, or replace multiple…
The Fermilab Accelerator Division, Instrumentation Department is adopting an open-source framework to replace our embedded VME-based data acquisition systems. Utilizing an iterative methodology, we first moved to embedded Linux, removing…
Deep reinforcement learning (RL) has led to many recent and groundbreaking advances. However, these advances have often come at the cost of both increased scale in the underlying architectures being trained as well as increased complexity…
We propose a novel algorithmic framework for distributional reinforcement learning, based on learning finite-dimensional mean embeddings of return distributions. We derive several new algorithms for dynamic programming and…
Solving partial differential equations (PDEs) by numerical methods meet computational cost challenge for getting the accurate solution since fine grids and small time steps are required. Machine learning can accelerate this process, but…
Early identification of stroke symptoms is essential for enabling timely intervention and improving patient outcomes, particularly in prehospital settings. This study presents a fast, non-invasive multimodal deep learning framework for…
AI accelerator processing capabilities and memory constraints largely dictate the scale in which machine learning workloads (e.g., training and inference) can be executed within a desirable time frame. Training a state of the art,…
In many embedded real-time systems, applications often interact with I/O devices via read/write operations, which may incur considerable suspension delays. Unfortunately, prior analysis methods for validating timing correctness in embedded…
A recent take towards Federated Analytics (FA), which allows analytical insights of distributed datasets, reuses the Federated Learning (FL) infrastructure to evaluate the summary of model performances across the training devices. However,…
In this paper, we study a new latency optimization problem for blockchain-based federated learning (BFL) in multi-server edge computing. In this system model, distributed mobile devices (MDs) communicate with a set of edge servers (ESs) to…
Particle accelerator beamline optimization is a high-dimensional control problem traditionally requiring significant expert intervention. We present RLABC (Reinforcement Learning for Accelerator Beamline Control), an open-source Python…
Optical approaches have made great strides towards the goal of high-speed, energy-efficient computing necessary for modern deep learning and AI applications. Read-in and read-out of data, however, limit the overall performance of existing…
Mobile Edge Computing (MEC), which incorporates the Cloud, edge nodes and end devices, has shown great potential in bringing data processing closer to the data sources. Meanwhile, Federated learning (FL) has emerged as a promising…