Reconfigurable On-Chip AI for Particle Physics Detectors with Logic Neural Networks

Abstract

On-device machine learning is increasingly important in applications where extreme data rates or resource constraints make centralized processing infeasible. Logic neural networks (LNNs), which directly learn Boolean logic instead of conventional arithmetic operations, have recently emerged as a state-of-the-art approach for efficient inference and are particularly well suited for deployment in custom silicon. However, hard-wired solutions are typically optimized for narrowly defined tasks and lack the ability to adapt to changing data distributions. Next-generation pixel detectors in particle physics present a particularly challenging use case: their high granularity and readout frequency generate data rates that cannot be centrally processed, while stringent space and power constraints necessitate highly efficient on-chip inference. Moreover, radiation damage progressively alters detector response, requiring models that can be re-trained and reconfigured after deployment. In this work, we evaluate LNNs for on-chip inference in pixel detectors. We show that their superior resource efficiency may enable a step change in model capability, making more complex architectures feasible within the available hardware budget. LNNs also provide increased robustness against radiation-induced random bit flips. Finally, we present novel work on reconfigurable LNNs, enabling models to adapt to changing operating conditions after deployment.

Ising noise filter: physics-informed filtering for particle detectors
I. Kharuk
The European Physical Journal C16 Oct 2026Peer-reviewedCC BY 4.0Full textHigh-energy & particle physicsCrossref
Leveraging Industrial Foundation Models at the Edge of Particle Physics Detectors via Distillation Learning and Hardware Co-design
Gia Ancone, Qibin Liu, Liangyu Wu +1
arXiv20 Sep 2026PreprintCC BY 4.0Full textApplied physics & instrumentation High-energy & particle physicsarXiv
Panda Diplomacy: Foundation Model Pre-training across Particle Imaging Detectors for High Energy and Nuclear Physics
Samuel Young, César Jesús-Valls, Kazuhiro Terao
arXiv1 Sep 2026PreprintCC BY 4.0Full textHigh-energy & particle physicsarXiv
Physics-guided deep neural networks for Laguerre–Gaussian modal decomposition via PCA-ranked Zernike descriptors
Malihe Karami, Saeed Ghavami Sabouri
Optics Express15 Oct 2026Peer-reviewedPublisher termsOptics & photonicsCrossref
Physics-informed neural networks for soliton solutions and parameter identification of the two-mode Korteweg–de Vries equation
Mohammad Akram, Umar Ishtiaq, Ioan-Lucian Popa
Nuclear Physics B30 Oct 2026Peer-reviewedCC BY 4.0Statistical & nonlinear physicsCrossref

Cite

BibTeX RIS

BibTeX

@misc{bileska2026reconfigurable,
  title = {{Reconfigurable On-Chip AI for Particle Physics Detectors with Logic Neural Networks}},
  author = {Mila Bileska and Lino Gerlach and Jennet Dickinson and Lindsey Gray and Giuseppe Di Guglielmo and Peter Elmer and Isobel Ojalvo},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.06816},
  eprint = {2610.06816},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.06816},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Reconfigurable On-Chip AI for Particle Physics Detectors with Logic Neural Networks
AU  - Mila Bileska
AU  - Lino Gerlach
AU  - Jennet Dickinson
AU  - Lindsey Gray
AU  - Giuseppe Di Guglielmo
AU  - Peter Elmer
AU  - Isobel Ojalvo
PY  - 2026
DA  - 2026/10/05
PB  - arXiv
DO  - 10.48550/arxiv.2610.06816
UR  - https://arxiv.org/abs/2610.06816
AB  - On-device machine learning is increasingly important in applications where extreme data rates or resource constraints make centralized processing infeasible. Logic neural networks (LNNs), which directly learn Boolean logic instead of conventional arithmetic operations, have recently emerged as a state-of-the-art approach for efficient inference and are particularly well suited for deployment in custom silicon. However, hard-wired solutions are typically optimized for narrowly defined tasks and lack the ability to adapt to changing data distributions. Next-generation pixel detectors in particle physics present a particularly challenging use case: their high granularity and readout frequency generate data rates that cannot be centrally processed, while stringent space and power constraints necessitate highly efficient on-chip inference. Moreover, radiation damage progressively alters detector response, requiring models that can be re-trained and reconfigured after deployment. In this work, we evaluate LNNs for on-chip inference in pixel detectors. We show that their superior resource efficiency may enable a step change in model capability, making more complex architectures feasible within the available hardware budget. LNNs also provide increased robustness against radiation-induced random bit flips. Finally, we present novel work on reconfigurable LNNs, enabling models to adapt to changing operating conditions after deployment.
ER  -

Abstract

Related

Cite