Neural Network by Ear: How to Capture a Particle's Energy ⚡ экспресс
Neural network architectures are presented for reconstructing the energy deposited in the cells of the ATLAS liquid-argon calorimeters under the high pile-up conditions expected at the HL-LHC. The networks are designed to run on readout electronics based on FPGAs with strict size and latency constraints. Fully connected (Dense), recurrent (RNN), and convolutional (CNN) networks are optimized using a Bayesian procedure that balances energy resolution and parameter count. The optimized Dense, CNN, and combined Dense+RNN architectures achieve a transverse energy resolution of about 80 MeV, surpassing both the currently used optimal filtering (OF) method and an RNN of comparable complexity. A detailed comparison across the full dynamic range shows that Dense, CNN, and Dense+RNN accurately reproduce the energy scale, whereas OF and RNN underestimate the energy. To obtain robust per-event uncertainties, Deep Evidential Regression is embedded in the Dense architecture; this approach provides predictive uncertainty estimates with minimal increase in network size.
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.
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.
🎯 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.