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

Gerrit Nolte

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

Machine Learning 2023-01-24 v1 Neural and Evolutionary Computing

Authors: Gerrit Nolte

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.

Keywords

geometric deep learning neural network architectures invariance equivariance theoretical evaluation master's thesis

Cite

@article{arxiv.2301.09381,
  title  = {A Structural Approach to the Design of Domain Specific Neural Network Architectures},
  author = {Gerrit Nolte},
  journal= {arXiv preprint arXiv:2301.09381},
  year   = {2023}
}

Comments

94 pages and 16 Figures Upload of my Master's thesis. Not peer reviewed and potentially contains errors

Related papers

View all related →