Deep learning and geometric deep learning: An introduction for mathematicians and physicists

DOI10.1142/S0219887823300064MaRDI QIDQ6144784zbMATH OpenOpenAlexFDO

Authors Rita Fioresi, Ferdinando Zanchetta

Publication date 29 January 2024

Published in International Journal of Geometric Methods in Modern Physics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2305.05601

zbMATH Keywords

machine learningmathematical physics

Mathematics Subject Classification ID

Mathematics for nonmathematicians (engineering, social sciences, etc.) (00A06) General topics in artificial intelligence (68T01)

Abstract: In this expository paper we want to give a brief introduction, with few key references for further reading, to the inner functioning of the new and successfull algorithms of Deep Learning and Geometric Deep Learning with a focus on Graph Neural Networks. We go over the key ingredients for these algorithms: the score and loss function and we explain the main steps for the training of a model. We do not aim to give a complete and exhaustive treatment, but we isolate few concepts to give a fast introduction to the subject. We provide some appendices to complement our treatment discussing Kullback-Leibler divergence, regression, Multi-layer Perceptrons and the Universal Approximation Theorem.

Recommendations

• Mathematics of deep learning. An introduction
• Deep learning: an introduction for applied mathematicians
• An introduction to the mathematics of deep learning
• The Modern Mathematics of Deep Learning
• Deep learning architectures. A mathematical approach

Cites work

• Graph Representation Learning
• scientific article; zbMATH DE number 1600999 (Why is no real title available?)
• scientific article; zbMATH DE number 7306852 (Why is no real title available?)
• Model-Centric Data Manifold: The Data Through the Eyes of the Model
• Multilayer feedforward networks are universal approximators
• Normalized graph Laplacians for directed graphs
• The elements of statistical learning. Data mining, inference, and prediction

Cited in

(2)

• The geometry of quantum computing
• GNN-enhanced TCN algorithms for ECG signal quality recognition

This page was built for publication: Deep learning and geometric deep learning: An introduction for mathematicians and physicists

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6144784)