Ehresmann connections and feedforward neural networks

DOI10.1016/S0895-7177(99)00078-3MaRDI QIDQ1596936zbMATH OpenOpenAlexFDO

Authors David William Pearson

Publication date 5 May 2002

Published in Mathematical and Computer Modelling (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/s0895-7177(99)00078-3

zbMATH Keywords

Ehresmann connectionsfeedforward neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Holomorphic feedforward networks
• Reconstructing a neural net from its output
• Universal approximations of invariant maps by neural networks
• Modeling connectionist network structures: Some geometric and categorical aspects
• Deep learning Gauss-Manin connections

Cites work

• A Theorem on Holonomy
• Approximating vertical vector fields for feedforward neural networks
• scientific article; zbMATH DE number 3892457 (Why is no real title available?)
• scientific article; zbMATH DE number 3228385 (Why is no real title available?)
• scientific article; zbMATH DE number 3086604 (Why is no real title available?)
• scientific article; zbMATH DE number 3086606 (Why is no real title available?)
• Learning representations by back-propagating errors

Cited in

(4)

• Holomorphic feedforward networks
• The connections of large perceptrons
• scientific article; zbMATH DE number 2079842 (Why is no real title available?)
• Cartan moving frames and the data manifolds

This page was built for publication: Ehresmann connections and feedforward neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1596936)