The Splendors and Miseries of Heavisidisation
This foundational work aims to enable ML applications across all natural sciences by addressing representation obstacles, though it is incremental as it only outlines early progress.
The paper tackles the problem of applying machine learning to scientific problems by requiring answers to be expressed as combinations of iterated Heaviside functions, and it describes initial steps toward reformulating science in these terms.
Machine Learning (ML) is applicable to scientific problems, i.e. to those which have a well defined answer, only if this answer can be brought to a peculiar form ${\cal G}: X\longrightarrow Z$ with ${\cal G}(\vec x)$ expressed as a combination of iterated Heaviside functions. At present it is far from obvious, if and when such representations exist, what are the obstacles and, if they are absent, what are the ways to convert the known formulas into this form. This gives rise to a program of reformulation of ordinary science in such terms -- which sounds like a strong enhancement of the constructive mathematics approach, only this time it concerns all natural sciences. We describe the first steps on this long way.