In the last few years, electron microscopy has experienced a new methodological paradigm
aimed to fix the bottlenecks and overcome the challenges of its analytical workflow. Machine …

Machine learning and artificial intelligence (ML/AI) are rapidly becoming an indispensable
part of physics research, with domain applications ranging from theory and materials …

Symmetry-based neural networks often constrain the architecture in order to achieve
invariance or equivariance to a group of transformations. In this paper, we propose an …

Abstract Test-time augmentation---the aggregation of predictions across transformed
versions of a test input---is a common practice in image classification. Traditionally …

Existing equivariant neural networks require prior knowledge of the symmetry group and
discretization for continuous groups. We propose to work with Lie algebras (infinitesimal …

Abstract Graph Neural Networks (GNNs) have become a prevailing tool for learning physical
dynamics. However, they still encounter several challenges: 1) Physical laws abide by …

Convolutions encode equivariance symmetries into neural networks leading to better
generalisation performance. However, symmetries provide fixed hard constraints on the …

Graph neural networks (GNNs) are commonly described as being permutation equivariant
with respect to node relabeling in the graph. This symmetry of GNNs is often compared to …

Despite the success of equivariant neural networks in scientific applications, they require
knowing the symmetry group a priori. However, it may be difficult to know which symmetry to …

Many successful deep learning architectures are equivariant to certain transformations in
order to conserve parameters and improve generalization: most famously, convolution …