Sign in

Lie Group Decompositions for Equivariant Neural Networks

By Mircea Mironenco and Patrick Forré at
LogoUniversity of Amsterdam
Invariance and equivariance to geometrical transformations have proven to be very useful inductive biases when training (convolutional) neural network models, especially in the low-data regime. Much work has focused on the case where the symmetry group employed is compact or abelian, or both. Recent work has explored enlarging the class... Show more
July 10, 2024
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Lie Group Decompositions for Equivariant Neural Networks
Click on play to start listening