A functional approach to interpreting the role of the adjoint equation in machine learning

DOI10.1007/s00025-023-02074-3MaRDI QIDQ6143226

Péter L. Simon, Andras Molnar, Imre Fekete

Publication date: 4 January 2024

Published in: Results in Mathematics (Search for Journal in Brave)

zbMATH Keywords

adjoint equationparameter learningcontinuous backpropagation

Mathematics Subject Classification ID

Computational learning theory (68Q32) Inverse problems involving ordinary differential equations (34A55) Methods of reduced gradient type (90C52)

Cites Work

• Unnamed Item
• Deep neural networks motivated by partial differential equations
• A proposal on machine learning via dynamical systems
• Adjoint Sensitivity Analysis for Differential-Algebraic Equations: The Adjoint DAE System and Its Numerical Solution
• Stable architectures for deep neural networks
• An Adjoint-Based Parameter Identification Algorithm Applied to Planar Cell Polarity Signaling

This page was built for publication: A functional approach to interpreting the role of the adjoint equation in machine learning