search

mohitsharma29 / ML-Reading-Group

Collection of talks given in the ML reading group@IIITD
10 stars 0 forks source link

Talk: Geometric Deep Learning #7

Open nikitamehrotra12 opened 4 years ago

nikitamehrotra12 commented 4 years ago

Convolutional Neural Networks, Recurrent Neural Networks, and other deep learning approaches have achieved unprecedented performance on a broad range of problems (e.g. Computer Vision and Speech Recognition). Despite the results obtained, the current research has mainly focused on data defined on Euclidean domains (i.e. grids). Nonetheless, in a multitude of different fields, such as Biology, Physics, Network Science, and Computer Graphics; one may have to deal with data defined on non-Euclidean domains (i.e. graphs and manifolds). Therefore to learn complex graph representations and relationships in the non-Euclidean domain geometric deep learning techniques are used.

A comprehensive survey of geometric deep learning - https://arxiv.org/abs/1901.00596

mohitsharma29 commented 4 years ago

@nikitamehrotra12 Will this talk be a condensed version of this survey paper?

nikitamehrotra12 commented 4 years ago

@mohitsharma29 no I just provided the link for the reference of GNNs. The talk will be based on the applications of GNN's in program analysis applications.

mohitsharma29 commented 4 years ago

Hey, Can you attach your presentation slides here and then close this issue?