Geometric Deep Learning¶
Bronstein, M. M., Bruna, Cohen, & Veličković, P. (2021). Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges. arXiv preprint.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Equivariance
- The concept emerges in pure mathematics (G-sets, equivariant functions, natural transformations) and recurs, under different names, as covariance in physics and as the design principle of geometric deep learning in machine learning, where Bronstein and colleagues (2021) treat it as a unifying organizing principle for neural architectures.
This sourceEstablishes equivariance/invariance under symmetry groups as the unifying organizing principle of modern neural architectures; shows pooling an equivariant feature yields an invariant one (group averaging onto the trivial representation).
- The concept emerges in pure mathematics (G-sets, equivariant functions, natural transformations) and recurs, under different names, as covariance in physics and as the design principle of geometric deep learning in machine learning, where Bronstein and colleagues (2021) treat it as a unifying organizing principle for neural architectures.
Verification¶
This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.
Registry ID ref:430ea186bee8 · see in the full table