cs.LGDec 11, 2025

Extrapolation of Periodic Functions Using Binary Encoding of Continuous Numerical Values

Authors: Brian P. Powell, Jordan A. Caraballo-Vega, Mark L. Carroll, Thomas Maxwell, Andrew Ptak, Greg Olmschenk, Jorge Martinez-Palomera

Organizations: NASA Goddard Space Flight Center, Greenbelt, MD 20771, USA · ARSC Federal Holding Company, Reston, VA 20190, USA · University of Maryland, College Park, MD 20190, USA · University of Maryland Baltimore County, Baltimore, MD 20190, USA

Abstract

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 four periodic waveforms without prior knowledge of their functional form. We contrast this finding with fixed Fourier encoding, which extrapolates well when the number of signal cycles over the normalized domain is an even integer and loses coherence at most other values, whereas NB2E degrades gradually away from those values and, except near odd cycle counts, remains substantially more accurate. These findings are limited to a single MLP architecture trained on one synthetic, exactly periodic, one-dimensional signal at a time, with extrapolation extending only to the end of the normalized domain. We do not propose a mechanism for this phenomenon. Rather, we present empirical observations which merit further study.

Figures & tables

Explore similar work

CardsList
  1. Evaluating Encoding Strategies for Closed-Loop Classification in Biological Neural Networks

    Jul 15, 2026Martin Schottlender, Veronika Volkova, Pengjie Zhou +3Neural EncodingSpike-Based Signal Encoding

  2. Encoding and Decoding Temporal Signals with Spiking Bandpass Wavelets

    May 10, 2026Jens Egholm Pedersen, Tony Lindeberg, Peter GerstoftSpike-Based Signal EncodingWavelet Methods