Machine learning of the well known things
This work addresses the problem of integrating known knowledge into machine learning frameworks, which could impact scientific and epistemological understanding, but it appears incremental as it builds on existing ML concepts without introducing new methods or data.
The paper investigates whether existing knowledge can be represented in the form of machine learning functions, specifically using Heaviside theta-functions, and provides elementary examples to demonstrate this possibility, suggesting a systematic reformulation approach.
Machine learning (ML) in its current form implies that an answer to any problem can be well approximated by a function of a very peculiar form: a specially adjusted iteration of Heavyside theta-functions. It is natural to ask if the answers to the questions, which we already know, can be naturally represented in this form. We provide elementary, still non-evident examples that this is indeed possible, and suggest to look for a systematic reformulation of existing knowledge in a ML-consistent way. Success or a failure of these attempts can shed light on a variety of problems, both scientific and epistemological.