Related papers: Hardware-Aware Design of a GNN-Based Hit Filtering…
An FPGA-based online trigger system has been developed for the COMET Phase-I experiment. This experiment searches for muon-to-electron conversion, which has never been observed yet. A drift chamber and trigger counters detect a…
After the current shutdown, the LHC is about to resume operation for a new data-taking period, when it will operate with increased luminosity, event rate and center of mass energy. The new conditions will impose more demanding constraints…
The ATLAS High Level Trigger (HLT) consists of two selection steps: the second level trigger and the event filter. Both will be implemented in software, running on mostly commodity hardware. Both levels have a coherent approach to event…
Collider experiments are equipped with trigger systems that rapidly inspect the physics content emerging from collisions to decide whether the resulting products are worth saving for later analysis. One crucial aspect for analyzing the…
The High Level Trigger (HLT) system of the ALICE experiment is an online event filter and trigger system designed for input bandwidths of up to 25 GB/s at event rates of up to 1 kHz. The system is designed as a scalable PC cluster,…
The High-Luminosity LHC (HL-LHC) will provide the unique opportunity to explore the nature of physics beyond the Standard Model of strong and electroweak interactions. Highly selective first-level triggers are essential for the physics…
Fine-tuning pre-trained foundation models has made significant progress in music information retrieval. However, applying these models to beat tracking tasks remains unexplored as the limited annotated data renders conventional fine-tuning…
The High Level Trigger (HLT) of the future ALICE heavy-ion experiment has to reduce its input data rate of up to 25 GB/s to at most 1.25 GB/s for output before the data is written to permanent storage. To cope with these data rates a large…
We implement a differentiable Neural Architecture Search (NAS) method inspired by FBNet for discovering neural networks that are heavily optimized for a particular target device. The FBNet NAS method discovers a neural network from a given…
The High-Luminosity LHC will provide the unique opportunity to explore the nature of physics beyond the Standard Model of strong and electroweak interactions. Highly selective first level triggers are essential for the physics programme of…
This work presents HAWX, a hardware-aware scalable exploration framework that employs multi-level sensitivity scoring at different DNN abstraction levels (operator, filter, layer, and model) to guide selective integration of heterogeneous…
Automatic algorithm-hardware co-design for DNN has shown great success in improving the performance of DNNs on FPGAs. However, this process remains challenging due to the intractable search space of neural network architectures and hardware…
Dynamic GNN inference has exhibited effectiveness in High Energy Physics (HEP) experiments at High Luminosity Large Hadron Collider (HL-LHC) due to strong capability to model complex particle interactions in collision events. Future HEP…
In order to achieve the data rates proposed for the future Run 3 upgrade of the LHCb detector, new processing models must be developed to deal with the increased throughput. For this reason, we aim to investigate the feasibility of purely…
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 proliferation of Internet of Things (IoT) devices has expanded the attack surface, necessitating efficient intrusion detection systems (IDSs) for network protection. This paper presents FLARE, a feature-based lightweight aggregation for…
The selective fixed-filter strategy is popular in industrial applications involving active noise control (ANC) technology, which circumvents the time-consuming online learning process by selecting the best-matched pre-trained control…
We propose a lightweight hybrid approach to clickbait detection that combines OpenAI semantic embeddings with six compact heuristic features capturing stylistic and informational cues. To improve efficiency, embeddings are reduced using PCA…
There is a need for fast adaptation in spike sorting algorithms to implement brain-machine interface (BMIs) in different applications. Learning and adapting the functionality of the sorting process in real-time can significantly improve the…
This paper proposes a hardware-efficient architecture, Linearized Convolution Network (LiCo-Net) for keyword spotting. It is optimized specifically for low-power processor units like microcontrollers. ML operators exhibit heterogeneous…