Prior knowledge meets neural ODEs: a two-stage training method for improved explainability
Neural Ordinary Differential Equations (ODEs) have been used extensively to model
physical systems because they represent a continuous-time function that can make …
physical systems because they represent a continuous-time function that can make …
Predicting Adverse Events for Patients with Type-1 Diabetes Via Self-Supervised Learning
Predicting blood glucose levels is fundamental for precise primary care of type-1 diabetes
(T1D) patients. However, it is challenging to predict glucose levels accurately, not to mention …
(T1D) patients. However, it is challenging to predict glucose levels accurately, not to mention …
A Two-Stage Training Method for Modeling Constrained Systems With Neural Networks
Real-world systems are often formulated as constrained optimization problems. Techniques
to incorporate constraints into Neural Networks (NN), such as Neural Ordinary Differential …
to incorporate constraints into Neural Networks (NN), such as Neural Ordinary Differential …
A Self-Adaptive Penalty Method for Integrating Prior Knowledge Constraints into Neural ODEs
The continuous dynamics of natural systems has been effectively modelled using Neural
Ordinary Differential Equations (Neural ODEs). However, for accurate and meaningful …
Ordinary Differential Equations (Neural ODEs). However, for accurate and meaningful …
Consistency Matters: Neural ODE Parameters are Dependent on the Training Numerical Method
Neural Ordinary Differential Equations (Neural ODEs) are continuous-depth models that use
an ordinary differential equation (ODE) to capture the dynamics of data. Due to their …
an ordinary differential equation (ODE) to capture the dynamics of data. Due to their …
Back to the Roots: A Suite of Xai Techniques for Understanding Neural Ordinary Differential Equations
Abstract Neural Ordinary Differential Equations (Neural ODEs) have emerged as a
promising approach for learning continuous-time functions from data using an ODE, offering …
promising approach for learning continuous-time functions from data using an ODE, offering …