Related papers: NuCLR: Nuclear Co-Learned Representations

We show examples of neutron capture, photo dissociation and Coulomb dissociation processes, relevant for studying nuclear structure properties of some light nuclei. In the case of the neutron capture, we show how interference effects among…

Several topics concerning nuclear structure and electromagnetic interactions of heavy nuclei are reviewed. These comprehend the deformed single-particle shell model, nuclear collective motion, symmetry breaking and approximate symmetry…

Elements of nuclear symmetry energy evaluated from different energy density functionals parametrized by fitting selective bulk properties of few representative nuclei are seen to vary widely. Those obtained from experimental data on nuclear…

Representation learning is the foundation for the recent success of neural network models. However, the distributed representations generated by neural networks are far from ideal. Due to their highly entangled nature, they are di cult to…

I review the main features of the nuclear response extracted from electron scattering data. The emerging picture clearly shows that the shell model does not provide a fully quantitative description of nuclear dynamics. On the other hand,…

Recent work has shown the potential of graph neural networks to efficiently predict material properties, enabling high-throughput screening of materials. Training these models, however, often requires large quantities of labelled data,…

In the first part, I give a brief description of the quark-gluon plasma search at CERN and of some experimental results. In the second part, I review a dynamical model of nucleus-nucleus interactions and propose a physical interpretation of…

Molecular representation learning contributes to multiple downstream tasks such as molecular property prediction and drug design. To properly represent molecules, graph contrastive learning is a promising paradigm as it utilizes…

Molecular Machine Learning (ML) bears promise for efficient molecule property prediction and drug discovery. However, labeled molecule data can be expensive and time-consuming to acquire. Due to the limited labeled data, it is a great…

In this work, we explore the use of deep learning techniques to learn how nuclear cross sections change as we add or remove protons and neutrons. As a proof of principle, we focus on the neutron-induced reactions in the fast energy regime.…

We present a new approach for predictive modeling and its uncertainty quantification for mechanical systems, where coarse-grained models such as constitutive relations are derived directly from observation data. We explore the use of a…

The exploration of nuclear mass or binding energy, a fundamental property of atomic nuclei, remains at the forefront of nuclear physics research due to limitations in experimental studies and uncertainties in model calculations,…

Deep Learning has been shown to learn efficient representations for structured data such as image, text or audio. In this chapter, we present neural network architectures that are able to learn efficient representations of molecules and…

Model-based reinforcement learning (RL) has proven to be a data efficient approach for learning control tasks but is difficult to utilize in domains with complex observations such as images. In this paper, we present a method for learning…

The predictive accuracy of Machine Learning (ML) models of molecular properties depends on the choice of the molecular representation. Based on the postulates of quantum mechanics, we introduce a hierarchy of representations which meet…

For a better understanding of the dynamics of exotic nuclei it is of crucial importance to develop a practical microscopic theory easy to be applied to a wide range of masses. Theoretically the basic task consists in formulating an easy…

Neutron-rich nuclei provide important insights to nuclear forces and to the nuclear equation of state. Advances in ab initio methods combined with new opportunities with rare isotope beams enable unique explorations of their properties…

The distribution of electric charge in atomic nuclei is fundamental to our understanding of the complex nuclear dynamics and a quintessential observable to validate nuclear structure models. We explore a novel approach that combines…

Nuclear structure and reaction theory are undergoing a major renaissance with advances in many-body methods, strong interactions with greatly improved links to Quantum Chromodynamics (QCD), the advent of high performance computing, and…

Molecular property prediction constitutes a cornerstone of drug discovery and materials science, necessitating models capable of disentangling complex structure-property relationships across diverse molecular modalities. Existing approaches…