7 papers
Equivariance and Augmentation for Bayesian Neural Networks
Miaowen Dong, Axel Flinth, Jan E. Gerken
Symmetries are important for many deep learning tasks, ranging from applications in the sciences to medical imaging. However, there is an ongoing debate about whether to impose sym…
Learning Chern Numbers of Topological Insulators with Gauge Equivariant Neural Networks
Longde Huang, Oleksandr Balabanov, Hampus Linander +3
Equivariant network architectures are a well-established tool for predicting invariant or equivariant quantities. However, almost all learning problems considered in this context f…
Finite-Width Neural Tangent Kernels from Feynman Diagrams
Max Guillen, Philipp Misof, Jan E. Gerken
Neural tangent kernels (NTKs) are a powerful tool for analyzing deep, non-linear neural networks. In the infinite-width limit, NTKs can easily be computed for most common architect…
PEAR: Equal Area Weather Forecasting on the Sphere
Hampus Linander, Tage Tykesson, Pietro Rosso +3
Artificial intelligence is rapidly reshaping the natural sciences, with weather forecasting emerging as a flagship AI4Science application where machine learning models can now riva…
From Layers to Networks: Comparing Neural Representations via Diffusion Geometry
Atharva Khandait, Jan E. Gerken
Diffusion geometry is a manifold learning framework that uses random walks defined by Markov transition matrices to characterize the geometry of a dataset at multiple scales. We us…
Criticality and Saturation in Orthogonal Neural Networks
Max Guillen, Jan E. Gerken
It has been known for a long time that initializing weight matrices to be orthogonal instead of having i.i.d. Gaussian components can improve training performance. This phenomenon…