NuCLR: Nuclear Co-Learned Representations

• URL: http://arxiv.org/abs/2306.06099v2
• Date: Fri, 21 Jul 2023 22:14:14 GMT
• Title: NuCLR: Nuclear Co-Learned Representations
• Authors: Ouail Kitouni, Niklas Nolte, Sokratis Trifinopoulos, Subhash Kantamneni, Mike Williams
• Abstract summary: We introduce Nuclear Co-Learned Representations (NuCLR), a deep learning model that predicts various nuclear observables. We report an intriguing finding that the learned representation of NuCLR exhibits the prominent emergence of crucial aspects of the nuclear shell model. This suggests that the model is capable of capturing the underlying physical principles and that our approach has the potential to offer valuable insights into nuclear theory.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce Nuclear Co-Learned Representations (NuCLR), a deep learning model that predicts various nuclear observables, including binding and decay energies, and nuclear charge radii. The model is trained using a multi-task approach with shared representations and obtains state-of-the-art performance, achieving levels of precision that are crucial for understanding fundamental phenomena in nuclear (astro)physics. We also report an intriguing finding that the learned representation of NuCLR exhibits the prominent emergence of crucial aspects of the nuclear shell model, namely the shell structure, including the well-known magic numbers, and the Pauli Exclusion Principle. This suggests that the model is capable of capturing the underlying physical principles and that our approach has the potential to offer valuable insights into nuclear theory.

Related papers

• Discovering Nuclear Models from Symbolic Machine Learning [0.0]
  We explore whether novel symbolic Machine Learning (ML) can rediscover traditional nuclear physics models. We developed a Multi-objective Iterated Regression approach that handles symbolic regressions over multiple target observables. Our approach identified simple analytical relationships based on the number of protons and neutrons, providing interpretable models with precision comparable to state-of-the-art nuclear models.
  arXiv  Detail & Related papers  (2024-04-17T15:32:58Z)
• Atomic and Subgraph-aware Bilateral Aggregation for Molecular Representation Learning [57.670845619155195]
  We introduce a new model for molecular representation learning called the Atomic and Subgraph-aware Bilateral Aggregation (ASBA) ASBA addresses the limitations of previous atom-wise and subgraph-wise models by incorporating both types of information. Our method offers a more comprehensive way to learn representations for molecular property prediction and has broad potential in drug and material discovery applications.
  arXiv  Detail & Related papers  (2023-05-22T00:56:00Z)
• Predicting nuclear masses with product-unit networks [0.0]
  We propose and explore a novel type of neural network for mass prediction in which the usual neuron-like processing units are replaced by complex-valued product units. Its performance is compared with that of several neural-network architectures, substantiating its suitability for nuclear mass prediction.
  arXiv  Detail & Related papers  (2023-05-08T12:51:16Z)
• Decoherence of Nuclear Spins in the Proximity of Nitrogen Vacancy Centers in Diamond [0.0]
  Nuclear spins in solids are promising platforms for quantum information processing. We study the nuclear decoherence processes in the vicinity of the nitrogen-vacancy (NV) center in diamond.
  arXiv  Detail & Related papers  (2023-02-07T04:58:38Z)
• Solving the nuclear pairing model with neural network quantum states [58.720142291102135]
  We present a variational Monte Carlo method that solves the nuclear many-body problem in the occupation number formalism. A memory-efficient version of the reconfiguration algorithm is developed to train the network by minimizing the expectation value of the Hamiltonian.
  arXiv  Detail & Related papers  (2022-11-09T00:18:01Z)
• Spectral density reconstruction with Chebyshev polynomials [77.34726150561087]
  We show how to perform controllable reconstructions of a finite energy resolution with rigorous error estimates. This paves the way for future applications in nuclear and condensed matter physics.
  arXiv  Detail & Related papers  (2021-10-05T15:16:13Z)
• Nuclei with up to $\boldsymbol{A=6}$ nucleons with artificial neural network wave functions [52.77024349608834]
  We use artificial neural networks to compactly represent the wave functions of nuclei. We benchmark their binding energies, point-nucleon densities, and radii with the highly accurate hyperspherical harmonics method.
  arXiv  Detail & Related papers  (2021-08-15T23:02:39Z)
• Electronic decay process spectra including nuclear degrees of freedom [49.1574468325115]
  We explore the ultra-rapid electronic motion spanning attoseconds to femtoseconds, demonstrating that it is equally integral and relevant to the discipline. The advent of ultrashort attosecond pulse technology has revolutionized our ability to directly observe electronic rearrangements in atoms and molecules.
  arXiv  Detail & Related papers  (2021-02-10T16:51:48Z)
• Theoretical methods for ultrastrong light-matter interactions [91.3755431537592]
  This article reviews theoretical methods developed to understand cavity quantum electrodynamics in the ultrastrong-coupling regime. The article gives a broad overview of the recent progress, ranging from analytical estimate of ground-state properties to proper computation of master equations. Most of the article is devoted to effective models, relevant for the various experimental platforms in which the ultrastrong coupling has been reached.
  arXiv  Detail & Related papers  (2020-01-23T18:09:10Z)
• Quantified limits of the nuclear landscape [0.24792948967354234]
  Predicting the range of particle-bound isotopes poses an appreciable challenge for nuclear theory. We use microscopic nuclear mass models and Bayesian methodology to provide quantified predictions of proton and neutron separation energies. The extrapolations obtained in this study will be put through stringent tests when new experimental information on exotic nuclei becomes available.
  arXiv  Detail & Related papers  (2020-01-16T16:25:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.