3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
Weiler et al.'s NeurIPS 2018 paper introducing SE(3)-equivariant CNNs for volumetric data using group theory and …...
Computer-Vision
IMG2SMI: Translating Molecular Structure Images to SMILES
Campos & Ji's method for converting 2D molecular images to SMILES strings using Transformers and SELFIES representation....
Rubik's Cube Player - Drexel Music Hackathon 2017
A hackathon project that converts Rubik's cube faces into music, creating more harmonious sounds as the cube becomes …