ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2506.09526
75
1

Neural Functions for Learning Periodic Signal

11 June 2025
Woojin Cho
Minju Jo
Kookjin Lee
Noseong Park
ArXiv (abs)PDFHTML
Main:10 Pages
39 Figures
Bibliography:4 Pages
18 Tables
Appendix:27 Pages
Abstract

As function approximators, deep neural networks have served as an effective tool to represent various signal types. Recent approaches utilize multi-layer perceptrons (MLPs) to learn a nonlinear mapping from a coordinate to its corresponding signal, facilitating the learning of continuous neural representations from discrete data points. Despite notable successes in learning diverse signal types, coordinate-based MLPs often face issues of overfitting and limited generalizability beyond the training region, resulting in subpar extrapolation performance. This study addresses scenarios where the underlying true signals exhibit periodic properties, either spatially or temporally. We propose a novel network architecture, which extracts periodic patterns from measurements and leverages this information to represent the signal, thereby enhancing generalization and improving extrapolation performance. We demonstrate the efficacy of the proposed method through comprehensive experiments, including the learning of the periodic solutions for differential equations, and time series imputation (interpolation) and forecasting (extrapolation) on real-world datasets.

View on arXiv
@article{cho2025_2506.09526,
  title={ Neural Functions for Learning Periodic Signal },
  author={ Woojin Cho and Minju Jo and Kookjin Lee and Noseong Park },
  journal={arXiv preprint arXiv:2506.09526},
  year={ 2025 }
}
Comments on this paper