Physics-based polynomial neural networks for one-shot learning of dynamical systems from one or a few samples

Abstract

This paper discusses an approach for incorporating prior physical knowledge into the neural network to improve data efficiency and the generalization of predictive models. If the dynamics of a system approximately follows a given differential equation, the Taylor mapping method can be used to initialize the weights of a polynomial neural network. This allows the fine-tuning of the model from one training sample of real system dynamics. The paper describes practical results on real experiments with both a simple pendulum and one of the largest worldwide X-ray source. It is demonstrated in practice that the proposed approach allows recovering complex physics from noisy, limited, and partial observations and provides meaningful predictions for previously unseen inputs. The approach mainly targets the learning of physical systems when state-of-the-art models are difficult to apply given the lack of training data.

References in corpus (7)

• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• Identifying nonlinear dynamical systems via generative recurrent neural networks with applications to fMRI
• Long-term Forecasting using Higher Order Tensor RNNs
• Learning Dynamical Systems from Partial Observations
• Matrix Lie Maps and Neural Networks for Solving Differential Equations
• ODE and Random Boolean networks in application to modelling of 6-mercaptopurine metabolism
• Physics-based Deep Learning