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.

We recently published a technical blog post discussing how ideas originating in quantum physics may be applied to overcome this barrier. We introduce new approaches for implementing these ideas efficiently in practice.

To learn more please see the full article published on Towards Data Science.

Further details can also be found in our related ICLR paper on Efficient Generalized Spherical CNNs.