DeepSphere swMATH ID: 29899 Software Authors: Nathanaël Perraudin, Michaël Defferrard, Tomasz Kacprzak, Raphael Sgier Description: DeepSphere: a spherical convolutional neural network. The code in this repository implements a generalization of Convolutional Neural Networks (CNNs) to the sphere. We here model the discretised sphere as a graph of connected pixels. The resulting convolution is more efficient (especially when data doesn’t span the whole sphere) and mostly equivariant to rotation (small distortions are due to the non-existence of a regular sampling of the sphere). The pooling strategy exploits a hierarchical pixelisation of the sphere (HEALPix) to analyse the data at multiple scales. The graph neural network model is based on ChebNet and its TensorFlow implementation. The performance of DeepSphere is demonstrated on a discrimination problem: the classification of convergence maps into two cosmological model classes Homepage: https://arxiv.org/abs/1810.12186 Source Code: https://github.com/SwissDataScienceCenter/DeepSphere Related Software: Healpix; FastPM; V-Net; nbodykit; CosmoFlow; GADGET; U-Net; Adam; PyTorch; Python; HexagDLy Cited in: 2 Documents all top 5 Cited by 8 Authors 1 Chen, Wei 1 Feng, Yu 1 He, Siyu 1 Ho, Shirley 1 Li, Yin 1 Póczos, Barnabás 1 Ravanbakhsh, Siamak 1 Simeoni, Matthieu Cited in 2 Serials 1 Proceedings of the National Academy of Sciences of the United States of America 1 Applied and Computational Harmonic Analysis Cited in 3 Fields 1 Calculus of variations and optimal control; optimization (49-XX) 1 Numerical analysis (65-XX) 1 Relativity and gravitational theory (83-XX) Citations by Year