Any-dimensional equivariant neural networks

• Published in: arXiv.org
• Main Authors: Levin, Eitan, Díaz, Mateo
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 29.04.2024
• Subjects: Computer architecture; Mapping; Neural networks; Numerical methods; Supervised learning; Topology

Traditional supervised learning aims to learn an unknown mapping by fitting a function to a set of input-output pairs with a fixed dimension. The fitted function is then defined on inputs of the same dimension. However, in many settings, the unknown mapping takes inputs in any dimension; examples in...