Enhancing continuous time series modelling with a latent ODE-LSTM approach

DOI10.1016/J.AMC.2024.128727zbMATH Open1545.65023MaRDI QIDQ6570985FDOQ6570985

Authors M. Fernanda P. Costa, Luis L. Ferrás

Publication date 11 July 2024

Published in Applied Mathematics and Computation (Search for Journal in Brave)

zbMATH Keywords

machine learningLSTMRNNneural ODEgradient clippinglatent ODElatent ODE-LSTM

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Learning and adaptive systems in artificial intelligence (68T05) Probabilistic models, generic numerical methods in probability and statistics (65C20)

Recommendations

• Revealing hidden dynamics from time-series data by ODENet
• Time-series learning of latent-space dynamics for reduced-order model closure
• Artificial Intelligence and Soft Computing - ICAISC 2004
• Continuous time modelling with individually varying time intervals for oscillating and non-oscillating processes
• An optimal control framework for adaptive neural ODEs

Cites work

• An Introduction to Variational Autoencoders
• Deep learning

This page was built for publication: Enhancing continuous time series modelling with a latent ODE-LSTM approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6570985)