On the effectiveness of neural priors in modeling dynamical systems
This work addresses the need for efficient neural network usage in dynamical systems modeling, though it appears incremental as it builds on existing coordinate network methods.
The paper tackles the problem of modeling dynamical systems by investigating the architectural regularization provided by neural networks, specifically coordinate networks, and demonstrates that simple networks with few layers can solve multiple modeling problems without explicit regularizers.
Modelling dynamical systems is an integral component for understanding the natural world. To this end, neural networks are becoming an increasingly popular candidate owing to their ability to learn complex functions from large amounts of data. Despite this recent progress, there has not been an adequate discussion on the architectural regularization that neural networks offer when learning such systems, hindering their efficient usage. In this paper, we initiate a discussion in this direction using coordinate networks as a test bed. We interpret dynamical systems and coordinate networks from a signal processing lens, and show that simple coordinate networks with few layers can be used to solve multiple problems in modelling dynamical systems, without any explicit regularizers.