Efficient Generalized Spherical CNNs

Hybrid rotationally equivariant spherical CNNs

Notions of spherical convolution offer a promising route to unlocking the potential of deep learning for the variety of problems in which spherical data are prevalent. However, the introduction of non-linearity is a challenge. In this post we explore how ideas originating in quantum physics may be applied to overcome this barrier. We introduce new approaches for implementing these ideas efficiently in practice. (Further details can be found in our related ICLR paper on Efficient …

artifical-intellegence cnns geometric-deep-learning machine learning physics thoughts-and-theory