Neural Network by Ear: How to Capture a Particle's Energy express

Original: "Optimised neural networks for online processing of ATLAS calorimeter data on FPGAs"

· Georges Aad, Raphael Bertrand, Lauri Laatu, Emmanuel Monnier, Arno Straessner, Nairit Sur, Johann C. Voigt

arXiv:2510.11469 · 2025-10-13 · CC BY 4.0 · 1 min

A neural network built into the detector listens in on the collider's noise and measures particle energy with record accuracy.

Measuring a particle’s energy at the Large Hadron Collider is like trying to catch a whisper in a roaring crowd. When protons collide, a flurry of particles is born, their signals blending into a cacophony. Old-school methods, like a noise-clogged ear, systematically underestimate the energy.

Scientists built a neural network that works right inside the detector. It tunes into the din and picks out the faint voice of the wanted particle. The top versions of the network are off by mere fractions of a percent — like mistaking 80 grains of sand out of a million. And while the network was trained on simulated events, it flawlessly recognizes real data.

The real gem: the network honestly tells you when it's unsure. Like a sound guy who says, “I think I hear a whisper, but I can’t swear to it.” That kind of candor guards against false discoveries.

Now physicists can study elusive particles, like dark matter, more precisely, even in heavy noise. And all this insight fits on a chip smaller than a matchbox.

Whole graph →

The ATLAS detector is as big as an eight-story building, but the neural network processing its signals fits on a chip smaller than a matchbox.

Scientists

Emmy Noether Wolfgang Pauli Enrico Fermi Paul Dirac Chien-Shiung Wu Eugene Wigner

Concepts

Recurrent Neural Networks neural network data reconstruction Large Language Models transformers reanalysis deep learning in medical imaging atlas detector neural network memory architecture Generative Adversarial Networks Natural Language Processing medical image analysis molecular dynamics acceleration active learning machine learning materials

I am the author

Neural Network by Ear: How to Capture a Particle's Energy express