A Structural Approach to the Design of Domain Specific Neural Network Architectures
arXiv:2301.09381
Abstract
This is a master's thesis concerning the theoretical ideas of geometric deep learning. Geometric deep learning aims to provide a structured characterization of neural network architectures, specifically focused on the ideas of invariance and equivariance of data with respect to given transformations. This thesis aims to provide a theoretical evaluation of geometric deep learning, compiling theoretical results that characterize the properties of invariant neural networks with respect to learning performance.
94 pages and 16 Figures Upload of my Master's thesis. Not peer reviewed and potentially contains errors