A Two-Stage Training Method for Modeling Constrained Systems With Neural Networks

arXiv:2403.02730v1 Announce Type: new
Abstract: Real-world systems are often formulated as constrained optimization problems. Techniques to incorporate constraints into Neural Networks (NN), such as Neural Ordinary Differential Equations (Neural ODEs), have been used. However, these introduce hyperparameters that require manual tuning through trial and error, raising doubts about the successful incorporation of constraints into the generated model. This paper describes in detail the two-stage training method for Neural ODEs, a simple, effective, and penalty parameter-free approach to model constrained systems. …

abstract arxiv constraints cs.ce cs.lg differential error math.oc modeling networks neural networks optimization ordinary stage systems through training type world