English

Induction and physical theory formation as well as universal computation by machine learning

General Physics 2021-05-20 v3

Abstract

Machine learning presents a general, systematic framework for the generation of formal theoretical models for physical description and prediction. Tentatively standard linear modeling techniques are reviewed; followed by a brief discussion of generalizations to deep forward networks for approximating nonlinear phenomena and universal computers.

Keywords

Cite

@article{arxiv.1609.03862,
  title  = {Induction and physical theory formation as well as universal computation by machine learning},
  author = {Alexander Svozil and Karl Svozil},
  journal= {arXiv preprint arXiv:1609.03862},
  year   = {2021}
}

Comments

6 pages; added a paragraph on the simulation of UTMs by ml algorithms

R2 v1 2026-06-22T15:48:25.865Z