J. Ngadiuba
YOU?
Author Swipe
View article: Fast jet tagging with MLP-Mixers on FPGAs
Fast jet tagging with MLP-Mixers on FPGAs Open
We explore the innovative use of MLP-Mixer models for real-time jet tagging and establish their feasibility on resource-constrained hardware like FPGAs. MLP-Mixers excel in processing sequences of jet constituents, achieving state-of-the-a…
View article: Interpreting Transformers for Jet Tagging
Interpreting Transformers for Jet Tagging Open
Machine learning (ML) algorithms, particularly attention-based transformer models, have become indispensable for analyzing the vast data generated by particle physics experiments like ATLAS and CMS at the CERN LHC. Particle Transformer (Pa…
View article: Interpreting and Accelerating Transformers for Jet Tagging
Interpreting and Accelerating Transformers for Jet Tagging Open
Attention-based transformers are ubiquitous in machine learning applications from natural language processing to computer vision. In high energy physics, one central application is to classify collimated particle showers in colliders based…
View article: Ultrafast jet classification at the HL-LHC
Ultrafast jet classification at the HL-LHC Open
Three machine learning models are used to perform jet origin classification. These models are optimized for deployment on a field-programmable gate array device. In this context, we demonstrate how latency and resource consumption scale wi…
View article: Robust anomaly detection for particle physics using multi-background representation learning
Robust anomaly detection for particle physics using multi-background representation learning Open
Anomaly, or out-of-distribution, detection is a promising tool for aiding discoveries of new particles or processes in particle physics. In this work, we identify and address two overlooked opportunities to improve anomaly detection (AD) f…
View article: Ultrafast jet classification at the HL-LHC
Ultrafast jet classification at the HL-LHC Open
Three machine learning models are used to perform jet origin classification. These models are optimized for deployment on a field-programmable gate array device. In this context, we demonstrate how latency and resource consumption scale wi…
View article: Reliable edge machine learning hardware for scientific applications
Reliable edge machine learning hardware for scientific applications Open
Extreme data rate scientific experiments create massive amounts of data that require efficient ML edge processing. This leads to unique validation challenges for VLSI implementations of ML algorithms: enabling bit-accurate functional simul…
View article: HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs
HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs Open
Neural networks with sub-microsecond inference latency are required by many critical applications. Targeting such applications deployed on FPGAs, we present High Granularity Quantization (HGQ), a quantization-aware training framework that …
View article: Reliable edge machine learning hardware for scientific applications
Reliable edge machine learning hardware for scientific applications Open
Extreme data rate scientific experiments create massive amounts of data that require efficient ML edge processing. This leads to unique validation challenges for VLSI implementations of ML algorithms: enabling bit-accurate functional simul…
View article: Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning
Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning Open
Anomaly, or out-of-distribution, detection is a promising tool for aiding discoveries of new particles or processes in particle physics. In this work, we identify and address two overlooked opportunities to improve anomaly detection for hi…
View article: Fast Particle-based Anomaly Detection Algorithm with Variational Autoencoder
Fast Particle-based Anomaly Detection Algorithm with Variational Autoencoder Open
Model-agnostic anomaly detection is one of the promising approaches in the search for new beyond the standard model physics. In this paper, we present Set-VAE, a particle-based variational autoencoder (VAE) anomaly detection algorithm. We …
View article: Efficient and Robust Jet Tagging at the LHC with Knowledge Distillation
Efficient and Robust Jet Tagging at the LHC with Knowledge Distillation Open
The challenging environment of real-time data processing systems at the Large Hadron Collider (LHC) strictly limits the computational complexity of algorithms that can be deployed. For deep learning models, this implies that only models wi…
View article: Corrigendum: Applications and techniques for fast machine learning in science
Corrigendum: Applications and techniques for fast machine learning in science Open
[This corrects the article DOI: 10.3389/fdata.2022.787421.].
View article: Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml
Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml Open
In this paper, we investigate how field programmable gate arrays can serve as hardware accelerators for real-time semantic segmentation tasks relevant for autonomous driving. Considering compressed versions of the ENet convolutional neural…
View article: Editorial: Efficient AI in particle physics and astrophysics
Editorial: Efficient AI in particle physics and astrophysics Open
Editorial: Efficient AI in particle physics and astrophysics
View article: Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml
Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml Open
In this paper, we investigate how field programmable gate arrays can serve as hardware accelerators for real-time semantic segmentation tasks relevant for autonomous driving. Considering compressed versions of the ENet convolutional neural…
View article: Compressing deep neural networks on FPGAs to binary and ternary precision with HLS4ML
Compressing deep neural networks on FPGAs to binary and ternary precision with HLS4ML Open
We present the implementation of binary and ternary neural networks in the hls4ml library, designed to automatically convert deep neural network models to digital circuits with FPGA firmware. Starting from benchmark models trained with flo…
View article: Applications and Techniques for Fast Machine Learning in Science
Applications and Techniques for Fast Machine Learning in Science Open
In this community review report, we discuss applications and techniques for fast machine learning (ML) in science—the concept of integrating powerful ML methods into the real-time experimental data processing loop to accelerate scientific …
View article: Physics Community Needs, Tools, and Resources for Machine Learning
Physics Community Needs, Tools, and Resources for Machine Learning Open
Machine learning (ML) is becoming an increasingly important component of cutting-edge physics research, but its computational requirements present significant challenges. In this white paper, we discuss the needs of the physics community r…
View article: Physics Community Needs, Tools, and Resources for Machine Learning
Physics Community Needs, Tools, and Resources for Machine Learning Open
Machine learning (ML) is becoming an increasingly important component of cutting-edge physics research, but its computational requirements present significant challenges. In this white paper, we discuss the needs of the physics community r…
View article: Improving Variational Autoencoders for New Physics Detection at the LHC With Normalizing Flows
Improving Variational Autoencoders for New Physics Detection at the LHC With Normalizing Flows Open
We investigate how to improve new physics detection strategies exploiting variational autoencoders and normalizing flows for anomaly detection at the Large Hadron Collider. As a working example, we consider the DarkMachines challenge datas…
View article: Lightweight Jet Reconstruction and Identification as an Object Detection Task
Lightweight Jet Reconstruction and Identification as an Object Detection Task Open
We apply object detection techniques based on deep convolutional blocks to end-to-end jet identification and reconstruction tasks encountered at the CERN Large Hadron Collider (LHC). Collision events produced at the LHC and represented as …
View article: Test-beam studies of diamond sensors for SLHC
Test-beam studies of diamond sensors for SLHC Open
Diamond sensors are studied as an alternative to silicon sensors to withstand the high radiation doses that are expected in future upgrades of the pixel detectors for the SLHC. Diamond pixel sensors are intrinsically radiation hard and are…
View article: The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider
The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collider Open
We describe the outcome of a data challenge conducted as part of the Dark Machines (https://www.darkmachines.org) initiative and the Les Houches 2019 workshop on Physics at TeV colliders. The challenged aims to detect signals of new physic…
View article: Report on 2105.14027v2
Report on 2105.14027v2 Open
We describe the outcome of a data challenge conducted as part of the Dark Machines (https://www.darkmachines.org)initiative and the Les Houches 2019 workshop on Physics at TeV colliders.The challenged aims to detect signals of new physics …
View article: fastmachinelearning/hls4ml: coris
fastmachinelearning/hls4ml: coris Open
What's Changed VivadoAccelerator backend: target pynq-z2 and zcu102 boards directly from hls4ml by @nicologhielmetti Updated PyTorch and ONNX converters by @Duchstf line_buffer Conv2D implementation for io_stream: reduced resource usage a…
View article: Applications and Techniques for Fast Machine Learning in Science
Applications and Techniques for Fast Machine Learning in Science Open
In this community review report, we discuss applications and techniques for fast machine learning (ML) in science -- the concept of integrating power ML methods into the real-time experimental data processing loop to accelerate scientific …