University of Cambridge > > Machine Learning @ CUED > Gauge Equivariant Convolutional Networks on Manifolds

Gauge Equivariant Convolutional Networks on Manifolds

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Adrian Weller.

Equivariance to symmetry transformations is one of the first rational principles for neural network architecture design. Equivariant networks have shown excellent performance on vision and medical imaging problems that exhibit symmetries. In this talk, I will show how this principle can be extended to data defined on general manifolds, using ideas from theoretical physics. We use the new theory to develop a highly practical and scalable alternative to Spherical CNNs, and show that this method outperforms previous methods on global climate pattern segmentation and omnidirectional vision.

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity