Quantum deep neural networks show promise for particle physics data analysis

Researchers have developed quantum-inspired deep neural networks (QDNNs) to extract Compton form factors (CFFs) from experimental data. These QDNNs were applied to data from the Thomas Jefferson National Accelerator Facility (JLab) using the twist-2 Belitsky-Kirchner-Müller formalism. Benchmarking against classical deep neural networks (CDNNs) using pseudodata showed that QDNNs achieved higher predictive accuracy and tighter uncertainties. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Quantum-inspired neural networks show promise for improved accuracy in complex physics data analysis, potentially influencing future research methodologies.

RANK_REASON This is a research paper detailing a new application of quantum-inspired deep neural networks to extract specific physics data.

Read on arXiv cs.LG →

• Compton Form Factor
• Quantum Deep Neural Networks
• Thomas Jefferson National Accelerator Facility
• JLab
• Belitsky-Kirchner-Müller formalism
• Classical Deep Neural Networks
• parton distributions
• hadronic structure

• paper
• other