copernicAI: Geometric AI for spherical data

Web

Today’s AI techniques have shown remarkable performance and are changing the world in which we live. However, the deep learning techniques that are leading to this AI revolution simply do not work with spherical data.

copernicAI unlocks the remarkable potential of deep learning for problems involving spherical data, in astrophysics, virtual reality and beyond.

code-hidden

Publications

Scalable and equivariant spherical CNNs by discrete-continuous (DISCO) convolutions

Preprint PDF Code

Scattering networks on the sphere for scalable and rotationally equivariant spherical CNNs

Preprint PDF Code

Efficient generalized spherical CNNs

Preprint PDF Code

Talks

Geometric deep learning on the sphere for the physical sciences

Jul 2023 London
PDF Code Code

Scalable and equivariant spherical CNNs by discrete-continuous (DISCO) convolutions

May 2023 Virtual
PDF Code Video

Geometric deep learning on the sphere: scalable and equivariant spherical CNNs

Oct 2022 CEA Saclay
PDF Code

Geometric deep learning on the sphere: scalable and equivariant spherical CNNs

Sep 2022 Cambridge
PDF Code

A brief introduction to geometric deep learning

May 2022 UCL
PDF Code

Geometric deep learning on the sphere: spherical CNNs and scattering networks

Apr 2022 Harwell (Remote)
PDF Code Video

Scattering networks on the sphere for scalable and rotationally equivariant spherical CNNs

Apr 2022 Virtual
PDF Code Video

Efficient generalized spherical CNNs

May 2021 Virtual
PDF Code Video

Geometric deep learning on the sphere: efficient generalized spherical CNNs

Apr 2021 London
PDF Code

Geometric deep learning on the sphere: efficient generalized spherical CNNs

Mar 2021 London
PDF Code Video

Deep learning on the celestial sphere

Dec 2020 London
PDF Code

Geometric deep learning on the sphere: efficient generalized spherical CNNs

Nov 2020 London
PDF Code

Geometric deep learning on the sphere: efficient generalized spherical CNNs

Oct 2020 London
PDF Code Video