Machine learning of the well known things
arXiv:2204.11613 · doi:10.1134/S0040577923030091
Abstract
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.
References in corpus (13)
- Machine learning and the physical sciences
- Deep Learning and its Application to LHC Physics
- New and Old Results in Resultant Theory
- Superintegrability summary
- Machine learning for complete intersection Calabi-Yau manifolds: a methodological study
- Interplay between MacDonald and Hall-Littlewood expansions of extended torus superpolynomials
- Machine Learning Lie Structures & Applications to Physics
- Nimble evolution for pretzel Khovanov polynomials
- Algebraic Geometry of Discrete Dynamics. The case of one variable
- Gaussian distribution of LMOV numbers
- Implications for colored HOMFLY polynomials from explicit formulas for group-theoretical structure
- Defect and degree of the Alexander polynomial
- Illuminating new and known relations between knot invariants