<ul data-eligibleForWebStory="true"><li>Deep neural networks are used as function approximators to represent various signal types, like periodic signals.</li><li>Recent approaches involve multi-layer perceptrons (MLPs) to learn nonlinear mappings from coordinates to signals.</li><li>MLPs face issues like overfitting and poor generalizability in learning continuous neural representations.</li><li>A new architecture is proposed to extract periodic patterns from measurements and enhance signal representation.</li><li>The proposed method aims to improve generalization and extrapolation performance for periodic signals.</li><li>Experiments demonstrate the effectiveness of the new architecture in learning periodic solutions for differential equations.</li><li>The method is also tested on real-world datasets for time series imputation and forecasting.</li></ul>

Neural Functions for Learning Periodic Signal

Discover more