Brauer's Group Equivariant Neural Networks
Jul 25, 2023
Speakers
Edward Pearce-Crump
Speaker · 0 followers
About
We provide a full characterisation of all of the possible group equivariant neural networks whose layers are some tensor power of $\mathbb{R}^{n}$ for three symmetry groups that are missing from the machine learning literature: $O(n)$, the orthogonal group; $SO(n)$, the special orthogonal group; and $Sp(n)$, the symplectic group. In particular, we find a spanning set of matrices for the learnable, linear, equivariant layer functions between such tensor power spaces in the standard basis of $\mathbb{R}^{n}$ when the group is $O(n)$ or $SO(n)$, and in the symplectic basis of $\mathbb{R}^{n}$ when the group is $Sp(n)$.We provide a full characterisation of all of the possible group equivariant neural networks whose layers are some tensor power of $\mathbb{R}^{n}$ for three symmetry groups that are missing from the machine learning literature: $O(n)$, the orthogonal group; $SO(n)$, the special orthogonal group; and $Sp(n)$, the symplectic group. In particular, we find a spanning set of matrices for the learnable, linear, equivariant layer functions between such tensor power spaces in the standard basis of $\mat…
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory
Watch later
Justin Cui, …
GPTs are as useful as their tools
Watch later
Learning Control-Oriented Dynamical Structure from Data
Watch later
Better Diffusion Models Further Improve Adversarial Training
Watch later
Zekai Wang, …
MODel: Memory Optimizations for Deep Learning
Watch later
IRNeXt: Rethinking Convolutional Network Design for Image Restoration
Watch later
Yuning Cui, …