Learning without relearning physical symmetry: an SO(3)-equivariant convolutional network (CNN) on the sphere
Paper recorded by Signals 4 on 2026-10-16 in cs.LG. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-16 on arXiv · recorded by Signals 4 on 2026-10-19
Category: cs.LG · 机器学习 · first seen 2026-10-19
Abstract
Many of the most important datasets in the physical sciences live natively on the sphere, and these data often carry no preferred position or orientation. Using methods that do not reflect this symmetry leads to far higher simulation requirements, which can be catastrophic for scientific analyses (forcing reliance on cheap, imperfect models that bias results). We present a novel spherical implemen
Read on arXiv →
Cite this page: Learning without relearning physical symmetry: an SO(3)-equivariant convolutional network (CNN) on the sphere: the #252 most recent of 749 cs.LG papers we have recorded (as of 2026-10-16). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/learning-without-relearning-physical-symmetry-an-so-3-equivariant-convolutional-.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free