paper-with-me

홈 › Papers

Extrapolation of Periodic Functions Using Binary Encoding of Continuous Numerical Values

2025-12-11 · Brian P. Powell, Jordan A. Caraballo-Vega, Mark L. Carroll, Thomas Maxwell, Andrew Ptak, Greg Olmschenk, Jorge Martinez-Palomera arxiv

We report the discovery that binary encoding allows neural networks to extrapolate periodic functions beyond their training bounds. We introduce Normalized Base-2 Encoding (NB2E) as a method for encoding continuous numerical values and demonstrate that, using this input encoding, vanilla multi-layer perceptrons (MLP) successfully extrapolate diverse periodic signals without prior knowledge of their functional form. Internal activation analysis reveals that NB2E induces bit-phase representations, enabling MLPs to learn and extrapolate signal structure independently of position.

📄 PDF Abstract BibTeX arXiv:2512.10817

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Periodic Extrapolative Generalisation in Neural Networks

2022-09-21 · Peter Belcák, Roger Wattenhofer

The learning of the simplest possible computational pattern -- periodicity -- is an open problem in the research of strong generalisation in neural networks. We formalise the problem of extrapolative generalisation for p…

Benchmarking

UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers

2025-11-25 · Min Zhao, Hongzhou Zhu, Yingze Wang, Bokai Yan 외 arxiv

Despite advances, video diffusion transformers still struggle to generalize beyond their training length, a challenge we term video length extrapolation. We identify two failure modes: model-specific periodic content rep…

Neural Networks Fail to Learn Periodic Functions and How to Fix It

2020-06-15 · NeurIPS 2020 12 · Liu Ziyin, Tilman Hartwig, Masahito Ueda

Previous literature offers limited clues on how to learn a periodic function using modern neural networks. We start with a study of the extrapolation properties of neural networks; we prove and demonstrate experimentally…

Inductive Bias

MEP: Multiple Kernel Learning Enhancing Relative Positional Encoding Length Extrapolation

2024-03-26 · Weiguo Gao

When the predicted sequence length exceeds the length seen during training, the transformer's inference accuracy diminishes. Existing relative position encoding methods, such as those based on the ALiBi technique, addres…

Self-Supervised Learning as Discrete Communication

2026-02-10 · Kawtar Zaher, Ilyass Moummad, Olivier Buisson, Alexis Joly arxiv

Most self-supervised learning (SSL) methods learn continuous visual representations by aligning different views of the same input, offering limited control over how information is structured across representation dimensi…

Self-Supervised LearningImage Classification