# Machine learning of the well known things

arXiv: https://arxiv.org/abs/2204.11613 · HTML: https://mlsanity.com/paper/2204.11613/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 25 references that are in the map.
- First posted on arXiv 25 Apr 2022.

## Builds on (most cited first, 3 of 3)

- [Machine learning for complete intersection Calabi-Yau manifolds: a methodological study](https://mlsanity.com/paper/2007.15706/) (2020)
- [Machine Learning Lie Structures & Applications to Physics](https://mlsanity.com/paper/2011.00871/) (2020)
- [Learning knot invariants across dimensions](https://mlsanity.com/paper/2112.00016/) (2021)

## Built on by (most cited first, 3 of 3)

- [A Triumvirate of AI Driven Theoretical Discovery](https://mlsanity.com/paper/2405.19973/) (2024)
- [The Splendors and Miseries of Heavisidisation](https://mlsanity.com/paper/2205.07377/) (2022)
- [A new Uncertainty Principle in Machine Learning](https://mlsanity.com/paper/2603.06634/) (2026)

## Abstract (arXiv)

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.