Group Equivariant Convolutional Networks.¶
Cohen, T. S., & Welling, M. (2016). Group Equivariant Convolutional Networks. Proceedings of the 33rd International Conference on Machine Learning (ICML), 2990-2999.
Cited by¶
2 citations across 2 artifacts.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Equivariance
- The structural insight is robust: a representation-theoretic intertwiner, a physical law written so it holds in every coordinate frame, a convolutional feature extractor whose output shifts when the image shifts, and a linear time-invariant filter whose response merely delays when the input is delayed are all the same shape, as Cohen and Welling (2016) demonstrate by deriving group-equivariant convolutional networks directly from the commuting-square condition.
This sourceDerives group-equivariant convolutional networks (G-CNNs) directly from the commuting (equivariance) condition, generalizing translation-equivariant CNNs to rotations and reflections via G-convolution.
- The structural insight is robust: a representation-theoretic intertwiner, a physical law written so it holds in every coordinate frame, a convolutional feature extractor whose output shifts when the image shifts, and a linear time-invariant filter whose response merely delays when the input is delayed are all the same shape, as Cohen and Welling (2016) demonstrate by deriving group-equivariant convolutional networks directly from the commuting-square condition.
- Invariance
- … symmetry of the action corresponds to a conserved quantity), topological invariants (genus, Euler characteristic, homotopy class) classify spaces up to deformation, loop invariants certify programs correct by identifying what is preserved across each iteration, and modern equivariant deep learning architectures
This sourceDerives group-equivariant convolutional networks directly from the commuting (equivariance) condition, generalizing translation-equivariant CNNs to rotations and reflections.
- … symmetry of the action corresponds to a conserved quantity), topological invariants (genus, Euler characteristic, homotopy class) classify spaces up to deformation, loop invariants certify programs correct by identifying what is preserved across each iteration, and modern equivariant deep learning 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:abfbb6fd65bd · see in the full table