https://towardsdatascience.com/geometric-foundations-of-deep-learning-94cdd45b451d?gi=d7fa7307aa63
Geometric foundations of Deep Learning
Geometric Deep Learning is an attempt for geometric unification of a broad class of ML problems from the perspectives of symmetry and invariance. These principles not only underlie the breakthrough performance of convolutional neural networks and the recent success of graph neural networks but also provide a principled way to construct new types of problem-specific inductive biases.
Michael Bronstein
Apr 28
“We believe that the current state of affairs in the field of deep (representation) learning is reminiscent of the situation of geometry in the nineteenth century… we now have a zoo of different neural network architectures for different kinds of data, but few unifying principles.”