A Structural Approach to the Design of Domain Specific Neural Network Architectures

2023/01/23 by Gerrit Nolte, Nolte, Gerrit
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE)

paper · pdf · doi:10.48550/arxiv.2301.09381

openalex publication_date 2023/01/23 · openalex created_date 2023/01/25 · openalex updated_date 2026/07/28

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.

Related

• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Geometric deep learning: going beyond Euclidean data
• The algebra and the geometry aspect of Deep learning
• How deep learning works --The geometry of deep learning
• Mathematics of Deep Learning