Score: 1

Extrapolation of Periodic Functions Using Binary Encoding of Continuous Numerical Values

Published: December 11, 2025 | arXiv ID: 2512.10817v1

By: Brian P. Powell , Jordan A. Caraballo-Vega , Mark L. Carroll and more

BigTech Affiliations: NASA

Potential Business Impact:

Makes computers learn patterns they haven't seen.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

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.

Country of Origin
🇺🇸 United States

Page Count
30 pages

Category
Computer Science:
Machine Learning (CS)