# Nanosecond machine learning event classification with boosted decision trees in FPGA for high energy physics

arXiv: https://arxiv.org/abs/2104.03408 · HTML: https://mlsanity.com/paper/2104.03408/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 91 references that are in the map.
- First posted on arXiv 7 Apr 2021.

## Builds on (most cited first, 14 of 14)

- [Fast inference of deep neural networks in FPGAs for particle physics](https://mlsanity.com/paper/1804.06913/) (2018)
- [Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors](https://mlsanity.com/paper/2006.10159/) (2020)
- [CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks](https://mlsanity.com/paper/1712.10321/) (2017)
- [hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices](https://mlsanity.com/paper/2103.05579/) (2021)
- [Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeters](https://mlsanity.com/paper/1705.02355/) (2017)
- [Compressing deep neural networks on FPGAs to binary and ternary precision with HLS4ML](https://mlsanity.com/paper/2003.06308/) (2020)
- [Fast convolutional neural networks on FPGAs with hls4ml](https://mlsanity.com/paper/2101.05108/) (2021)
- [Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics](https://mlsanity.com/paper/2008.03601/) (2020)
- [Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference](https://mlsanity.com/paper/2102.11289/) (2021)
- [Fast inference of Boosted Decision Trees in FPGAs for particle physics](https://mlsanity.com/paper/2002.02534/) (2020)
- [Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs](https://mlsanity.com/paper/2012.01563/) (2020)
- [Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics](https://mlsanity.com/paper/2012.00173/) (2020)
- [Towards Efficient and Scalable Acceleration of Online Decision Tree Learning on FPGA](https://mlsanity.com/paper/2009.01431/) (2020)
- [An Algebra to Merge Heterogeneous Classifiers](https://mlsanity.com/paper/1501.05141/) (2015)

## Built on by (most cited first, 9 of 9)

- [Machine Learning in the Search for New Fundamental Physics](https://mlsanity.com/paper/2112.03769/) (2021)
- [PELICAN: Permutation Equivariant and Lorentz Invariant or Covariant Aggregator Network for Particle Physics](https://mlsanity.com/paper/2211.00454/) (2022)
- [Online-compatible Unsupervised Non-resonant Anomaly Detection](https://mlsanity.com/paper/2111.06417/) (2021)
- [Ultrafast jet classification on FPGAs for the HL-LHC](https://mlsanity.com/paper/2402.01876/) (2024)
- [Snowmass 2021 Computational Frontier CompF03 Topical Group Report: Machine Learning](https://mlsanity.com/paper/2209.07559/) (2022)
- [rule4ml: An Open-Source Tool for Resource Utilization and Latency Estimation for ML Models on FPGA](https://mlsanity.com/paper/2408.05314/) (2024)
- [Physics Community Needs, Tools, and Resources for Machine Learning](https://mlsanity.com/paper/2203.16255/) (2022)
- [Accelerating Cavity Fault Prediction Using Deep Learning at Jefferson Laboratory](https://mlsanity.com/paper/2404.15829/) (2024)
- [BitHEP -- The Limits of Low-Precision ML in HEP](https://mlsanity.com/paper/2504.03387/) (2025)

## Abstract (arXiv)

We present a novel implementation of classification using the machine learning / artificial intelligence method called boosted decision trees (BDT) on field programmable gate arrays (FPGA). The firmware implementation of binary classification requiring 100 training trees with a maximum depth of 4 using four input variables gives a latency value of about 10 ns, independent of the clock speed from 100 to 320 MHz in our setup. The low timing values are achieved by restructuring the BDT layout and reconfiguring its parameters. The FPGA resource utilization is also kept low at a range from 0.01% to 0.2% in our setup. A software package called fwXmachina achieves this implementation. Our intended user is an expert of custom electronics-based trigger systems in high energy physics experiments or anyone that needs decisions at the lowest latency values for real-time event classification. Two problems from high energy physics are considered, in the separation of electrons vs. photons and in the selection of vector boson fusion-produced Higgs bosons vs. the rejection of the multijet processes.