The paper titled "Fast muon tracking with machine learning implemented in FPGA" was published in Nuclear Instruments and Methods in Physics Research Section A. Chang Sun and Takumi Nakajima authored the paper with Yuki Mitsumori, Associate Prof. Yasuyuki Horii and Professor Makoto Tomoto.

This paper describes a new approach for fast tracking on a multiwire proportional chamber with neural networks. The ATLAS experiment at the LHC uses a muon trigger that reconstructs muon tracks and selects high-momentum ones produced by decays of heavy particles. The authors developed two compact and quantized neural network models: a convolutional neural network and a multistage neural network optimized for the detector configuration of the thin gap chambers at the ATLAS experiment. Furthermore, they implemented the networks in FPGA with sufficiently high angular resolution and short latency. Please refer to the paper for details.

Paper information:
Chang Sun, Takumi Nakajima, Yuki Mitsumori, Yasuyuki Horii and Makoto Tomoto, "Fast muon tracking with machine learning implemented in FPGA"
[Nucl. Instrum. Methods Phys. Res. A, 1045, 167546 (2023). DOI:10.1016/j.nima.2022.167546]