Deep Learning with symmetries

Tess Smidt will discuss how to create convolutional neural networks that have the symmetries of Euclidean space (3D translation- and rotation-equivariance) which allows them to identify features in any orientation or location in an example with the same filters. These properties are especially useful for dealing with the geometry of physical systems. Arxiv: https://arxiv.org/abs/1802.08219.

The Berkeley Statistics and Machine Learning Discussion Group meets weekly to discuss current applications across a wide variety of research domains and software methodologies. Register here to view, propose and vote for this group's upcoming discussion topics. All interested members of the UC Berkeley and LBL communities are welcome and encouraged to attend. Questions may be directed to François Lanusse.