Related papers: The Development of ADS Virtual Accelerator Based o…

The architecture for Spallation Neutron Source accelerator physics application programs is presented. These high level applications involve processing and managing information from the diagnostic instruments, the machine control system,…

Artificial Neural Network is one of the most common AI application fields. This field has direct and indirect usages most sciences. The main goal of ANN is to imitate biological neural networks for solving scientific problems. But the level…

Deep active learning (DAL) seeks to reduce annotation costs by enabling the model to actively query instance annotations from which it expects to learn the most. Despite extensive research, there is currently no standardized evaluation…

Turning the current experimental plasma accelerator state-of-the-art from a promising technology into mainstream scientific tools depends critically on high-performance, high-fidelity modeling of complex processes that develop over a wide…

First Experiences Integrating PC Distributed I/O Into Argonne's ATLAS Control System The roots of ATLAS (Argonne Tandem-Linac Accelerator System) date back to the early 1960s. Located at the Argonne National Laboratory, the accelerator has…

Active learning (AL), which aims to construct an effective training set by iteratively curating the most formative unlabeled data for annotation, has been widely used in low-resource tasks. Most active learning techniques in classification…

Incremental learning is a machine learning paradigm where a model learns from a sequential stream of tasks. This setting poses a key challenge: balancing plasticity (learning new tasks) and stability (preserving past knowledge). Neural…

Over the past few years, the explosion in sparse tensor algebra workloads has led to a corresponding rise in domain-specific accelerators to service them. Due to the irregularity present in sparse tensors, these accelerators employ a wide…

In recent years, rapid progress has been made in developing artificial intelligence (AI) and machine learning (ML) methods for x-ray absorption spectroscopy (XAS) analysis. Compared to traditional XAS analysis methods, AI/ML approaches…

Following the motivation for an Accelerator Driven System (ADS), the requirements on the accelerator are derived. Using the MYRRHA project as example, the beam optics/dynamics design and operational concept of such an accelerator are…

Many sophisticated computer models have been developed to understand the behaviour of particle accelerators. Even these complex models often do not describe the measured data. Interactions of the beam with external fields, other particles…

Special-purpose hardware accelerators are increasingly pivotal for sustaining performance improvements in emerging applications, especially as the benefits of technology scaling continue to diminish. However, designers currently lack…

This paper proposes asal, a new GAN based active learning method that generates high entropy samples. Instead of directly annotating the synthetic samples, ASAL searches similar samples from the pool and includes them for training. Hence,…

Developing complex, reliable advanced accelerators requires a coordinated, extensible, and comprehensive approach in modeling, from source to the end of beam lifetime. We present highlights in Exascale Computing to scale accelerator…

The wide adoption of Machine Learning technologies has created a rapidly growing demand for people who can train ML models. Some advocated the term "machine teacher" to refer to the role of people who inject domain knowledge into ML models.…

In-vehicle communication technologies are evolving. While today's cars are equipped with fieldbusses to interconnect the various electronic control units, next generation vehicles have timing and bandwidth requirements that exceed the…

Large language models (LLMs) exhibit memory-intensive behavior during decoding, making it a key bottleneck in LLM inference. To accelerate decoding execution, hybrid-bonding-based 3D-DRAM has been adopted in LLM accelerators. While this…

Deep learning (DL) models are piquing high interest and scaling at an unprecedented rate. To this end, a handful of tiled accelerators have been proposed to support such large-scale training tasks. However, these accelerators often…

For the proper operation of Dalian Compact Light Source (DCLS) linac, measurement and control of the electron bunch is critical. In order to test control algorithms and high level physical applications, a virtual accelerator environment is…

The high efficiency of domain-specific hardware accelerators for machine learning (ML) has come from specialization, with the trade-off of less configurability/ flexibility. There is growing interest in developing flexible ML accelerators…