Improved Initialization for Port-Hamiltonian Neural Network Models

TL;DR

This paper introduces an improved initialization method for port-Hamiltonian neural networks, which enhances training convergence and reduces training time by starting from a linear system estimate before adapting to nonlinearities.

Contribution

The paper proposes a novel initialization technique based on linear system estimation to improve port-Hamiltonian neural network training.

Findings

Better convergence compared to original method

Reduced training times across experiments

Effective in noisy environments

Abstract

Port-Hamiltonian neural networks have shown promising results in the identification of nonlinear dynamics of complex systems, as their combination of physical principles with data-driven learning allows for accurate modelling. However, due to the non-convex optimization problem inherent in learning the correct network parameters, the training procedure is prone to converging to local minima, potentially leading to poor performance. In order to avoid this issue, this paper proposes an improved initialization for port-Hamiltonian neural networks. The core idea is to first estimate a linear port-Hamiltonian system to be used as an initialization for the network, after which the neural network adapts to the system nonlinearities, reducing the training times and improving convergence. The effectiveness of this method is tested on a chained mass-spring-damper setup for varying noise levels and compared to the original approach.