Events2Join

Equivariant Neural Operators for Gradient|Consistent Topology ...


Modeling Earth's Atmosphere with Spherical Fourier Neural Operators

Thus, we strive to establish a formulation that remains equivariant under rotations. ... While a broad variety of neural network topologies such ...

Dr. David Erzmann - Center for Industrial Mathematics - Uni Bremen

D. Erzmann, S. Dittmer. Equivariant Neural Operators for gradient-Consistent Topology Optimization . Journal of Computational Design and Engineering, 11(3):91- ...

Equivariant Neural Networks Utilizing Molecular Clusters for ...

... topology-based structure generation, (75) and rotational mutation strategies. ... consistent with the literature, which notes a slight ...

Equivariant neural networks for spin dynamics simulations of ...

I present a novel equivariant neural network architecture for the large-scale spin dynamics simulation of the Kondo lattice model.

T036 · An introduction to E(3)-invariant graph neural networks

Recent work from 2022 uses E(3) equivariant graph neural networks as the backbone for a generative model that learns to predict potential ligand docking ...

The Changing Role of Mathematics in Machine Learning Research

Topological tools such as homology, which counts the number of holes in a space, has been used to illuminate the way that neural networks ...

Spherical Fourier Neural Operators: Learning Stable Dynamics on ...

A novel SFNO equivariant architecture for modeling nonlinear chaotic dynamical systems on the sphere. • Theoretical extension of FNOs to spherical geometry,.

PDE-Based Group Equivariant Convolutional Neural Networks - Pure

More recent work in this direction includes integrating equivariant partial differential operators in steerable CNNs. [75], drawing a strong ...

Rotationally equivariant super-resolution of velocity fields in two ...

These theoretical assertions are supported by the results of numerical experiments, where two existing convolutional neural networks (CNNs) are ...

A new paradigm for artificial intelligence based on group equivariant ...

Equivariant operators are proving to be increasingly important in deep learning, in order to make neural networks more transparent and ...

EGraFFBench: evaluation of equivariant graph neural network force ...

Equivariant graph neural network force fields (EGraFFs) have shown great promise in modelling complex interactions in atomic systems by ...

General framework for E(3)-equivariant neural network ...

Fundamental symmetries are crucial to the deep-learning modeling of physical systems. Here the authors use equivariant neural networks ...

Policy Gradient Methods in the Presence of Symmetries and State ...

Tensor field networks: Rotation-and translation-equivariant neural net- works for 3d point clouds. ... generates its topology and the resulting metric space is ...

Beyond Message Passing: a Physics-Inspired Paradigm for Graph ...

Maron et al. Invariant and equivariant graph networks (2019) ICLR, can also be put in this category. [56] Connection is an object in ...

E(n) Equivariant Graph Neural Network for Learning Interactional ...

We have developed a multi-input E(n) equivariant graph convolution-based model designed for the prediction of chemical properties that result from the ...

NeurIPS 2024 Papers

Approximately Equivariant Neural Processes · Semi-Supervised Sparse Gaussian ... Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix ...

On Non-Linear operators for Geometric Deep Learning - HAL

Let us remark that the study of equivariant operators that take as input vector fields is motivated by the use of Neural Networks in physics, in ...

Equivariant neural networks for spin dynamics simulations of ...

(a) Hz dependences of the topological number |nsk| and the magnetization |Mz| obtained by the ML-LLG simulation. (b)–(d) Configurations of ...

Equivariant convolutional networks. - Research Explorer

We present a sequence of increasingly general group equivariant convolutional neural networks (G-. CNNs), adapted to the particular symmetries of various spaces ...

CNNs on surfaces using rotation-equivariant features

This paper is concerned with a fundamental problem in geometric deep learning that arises in the construction of convolutional neural ...