An ODE-based neural network with Bayesian optimization

DOI10.14495/JSIAML.15.101MaRDI QIDQ6139497zbMATH OpenOpenAlexFDO

Authors Hirotada Honda, Takashi Sano, Shugo Nakamura

Publication date 19 December 2023

Published in JSIAM Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.14495/jsiaml.15.101

zbMATH Keywords

acquisition functionBayesian optimizationneural ODE

Mathematics Subject Classification ID

Numerical methods for variational inequalities and related problems (65K15) Numerical investigation of stability of solutions to ordinary differential equations (65L07) Artificial neural networks and deep learning (68T07)

Recommendations

• Solving ordinary differential equations using an optimization technique based on training improved artificial neural networks
• A numerical method for solving ordinary differential equations by using neural network
• Regression-based neural network training for the solution of ordinary differential equations
• Shooting neural networks algorithm for solving boundary value problems in ODEs
• Laplace based Bayesian inference for ordinary differential equation models using regularized artificial neural networks

Cites work

• A mean-field optimal control formulation of deep learning
• A proposal on machine learning via dynamical systems
• Application of Bayesian approach to numerical methods of global and stochastic optimization
• Convexity, Classification, and Risk Bounds
• Deep neural networks motivated by partial differential equations
• Differential evolution -- a simple and efficient heuristic for global optimization over continuous spaces

Cited in

(3)

• Laplace based Bayesian inference for ordinary differential equation models using regularized artificial neural networks
• Large-scale Bayesian optimal experimental design with derivative-informed projected neural network
• A hybrid Sobolev gradient method for learning NODEs

This page was built for publication: An ODE-based neural network with Bayesian optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6139497)