Exploring quaternion neural network loss surfaces

DOI10.1007/s00006-024-01313-2MaRDI QIDQ6550948

Jeremiah Bill, Bruce Cox

Publication date: 5 June 2024

Published in: Advances in Applied Clifford Algebras (Search for Journal in Brave)

zbMATH Keywords

dimensionality reductiongradient descent optimizationsurface curvaturequaternion neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Time series analysis of dynamical systems (37M10) Neural nets and related approaches to inference from stochastic processes (62M45) Applications of Clifford algebras to physics, etc. (15A67)

Cites Work

• Title not available (Why is that?)
• Multilayer feedforward networks are universal approximators
• On Clifford neurons and Clifford multi-layer perceptrons
• Automatic multivector differentiation and optimization
• Deterministic Nonperiodic Flow
• Mathematical Pearls: A Proof of Liouville's Theorem
• Approximation by superpositions of a sigmoidal function

Related Items (1)

STP method for solving the least squares special solutions of quaternion matrix equations

This page was built for publication: Exploring quaternion neural network loss surfaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6550948)