A Structural Approach to the Design of Domain Specific Neural Network Architectures
It addresses the need for theoretical foundations in domain-specific neural network design, but it is incremental as it compiles existing ideas without introducing new methods.
This master's thesis tackles the problem of theoretically evaluating geometric deep learning by compiling results that characterize how invariant neural networks affect learning performance, but it does not provide concrete numerical results.
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.