Related papers: Fast Muon Tracking with Machine Learning Implement…

Convolutional Neural Networks (CNNs) have gained significant traction in the field of machine learning, particularly due to their high accuracy in visual recognition. Recent works have pushed the performance of GPU implementations of CNNs…

We present a neural network architecture and training method designed to enable very rapid training and low implementation complexity. Due to its training speed and very few tunable parameters, the method has strong potential for…

Large neural networks achieve state-of-the-art performance on many tasks, yet their sheer size hinders deployment on resource-constrained devices. Among existing compression approaches, cross-layer parameter sharing remains relatively…

The 9600 channels of the multi-wire proportional chamber of the H1 experiment at HERA have to be read out within 96 ns and made available to the trigger system. The tight spatial conditions at the rear end flange require a compact…

The influence of fast neutrons on the occupancy and the single tube resolution of ATLAS muon drift detectors was investigated by exposing a chamber built out of 3 layers of 3 short standard drift tubes to neutron flux-densities of up to 16…

Perfect alignment in chosen beam sectors at both transmit- and receive-nodes is required for beamforming in mmWave bands. Current 802.11ad WiFi and emerging 5G cellular standards spend up to several milliseconds exploring different sector…

Highly selective triggers are essential for the physics programme of the ATLAS experiment at HL-LHC where the instantaneous luminosity will be about an order of magnitude larger than the LHC instantaneous luminosity in Run 1. The first…

The detection of photons produced during the avalanche development in gas chambers has been the subject of detailed studies in the past. The great progresses achieved in last years in the performance of micro-pattern gas detectors on one…

Thin gap chambers (TGCs) are used for the muon trigger system in the forward region of the LHC experiment ATLAS. A TGC consists of a plane of closely spaced wires maintained at positive high voltage, sandwiched between resistive grounded…

Modern mobile neural networks with a reduced number of weights and parameters do a good job with image classification tasks, but even they may be too complex to be implemented in an FPGA for video processing tasks. The article proposes…

We show that Transformer encoder architectures can be sped up, with limited accuracy costs, by replacing the self-attention sublayers with simple linear transformations that "mix" input tokens. These linear mixers, along with standard…

The high-luminosity phase of the Large Hadron Collider (HL-LHC) will result in ten times higher particle background than measured during the first phase of LHC operation. In order to fully exploit the highly-demanding operating conditions…

A Monte Carlo k-nearest neighbours (KNN) and a multi-resolution convolutional neural network (CNN) were developed to detect the presences of multiple gasses in near infrared (IR) spectrums. High Resolution Transmission database was used to…

This paper presents a 1-D convolutional graph neural network for fault detection in microgrids. The combination of 1-D convolutional neural networks (1D-CNN) and graph convolutional networks (GCN) helps extract both spatial-temporal…

With the HL-LHC upgrade of the LHC machine, an increase of the instantaneous luminosity by a factor of five is expected and the current detection systems need to be validated for such working conditions to ensure stable data taking. At the…

Convolutional neural networks are modern models that are very efficient in many classification tasks. They were originally created for image processing purposes. Then some trials were performed to use them in different domains like natural…

In this work we describe a parallel geometry gaseous detector constituted by a thin (0.6 mm) amplifying gap preceded by a drift region. The gap is delimited by a metal plate and by a wire mesh. The detector can count up to a rate of 10^7…

While task-specific finetuning of pretrained networks has led to significant empirical advances in NLP, the large size of networks makes finetuning difficult to deploy in multi-task, memory-constrained settings. We propose diff pruning as a…

Graph Neural Networks (GNNs) have shown great superiority on non-Euclidean graph data, achieving ground-breaking performance on various graph-related tasks. As a practical solution to train GNN on large graphs with billions of nodes and…

The Liquid Argon Time Projection Chamber (LArTPC) is an advanced neutrino detector technology widely used in recent and upcoming accelerator neutrino experiments. It features a low energy threshold and high spatial resolution that allow for…