A Taylor Based Sampling Scheme for Machine Learning in Computational Physics
This work addresses a domain-specific problem in computational physics for improving surrogate models, but it appears incremental as it builds on existing sampling methods.
The authors tackled the problem of reducing error in deep neural networks when learning solutions of ordinary differential equations by developing a new data sampling scheme based on Taylor approximation, achieving accuracy gains without performance cost.
Machine Learning (ML) is increasingly used to construct surrogate models for physical simulations. We take advantage of the ability to generate data using numerical simulations programs to train ML models better and achieve accuracy gain with no performance cost. We elaborate a new data sampling scheme based on Taylor approximation to reduce the error of a Deep Neural Network (DNN) when learning the solution of an ordinary differential equations (ODE) system.