EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A framework for visual-mathematical literacy in applied machine learning: why representation choices shape what models can learn

Gaurav Singh, Rahul Singh Dhari

Machine Learning: Engineering · 01.12.2026 · 2 (2) · 025004

DOI: 10.1088/3049-4761/ae7df3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning: Engineering, online erschienen am 27.07.2026. Verfasst von Gaurav Singh und 1 weiteren Autor:innen. Die Arbeit nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine learning (ML) is increasingly applied to physical and engineering systems, yet the translation of physical phenomena into model inputs has received limited systematic scrutiny. The upstream decisions that determine what the model can learn and how its outputs should be interpreted are typically treated as implementation details, but they embed inductive bias in the model. A review of 28 applied ML studies from materials, mechanics and computational materials science (2007–2025) found that all reported basic representation parameters, but only 21% systematically compared alternative representations; the pattern is indicative of a structural rather than merely incidental gap, with the transparency deficit persisting within the most mature and comparison-friendly class (CNN image pipelines). To address this gap, the paper introduces visual-mathematical literacy: a framework for reasoning about and evaluating representation choices, drawing on representation learning, inductive bias analysis, physics-informed ML, and design epistemology. A case study in auxetic metamaterial classification is developed in two phases: a retrospective analysis of six representation decisions across a three-stage pipeline, and a prospective audit executing each of the ten protocol questions end-to-end against a reproduction of the pipeline, showing which decisions the protocol corroborates, refines, and opens. The paper concludes with a protocol of ten audit questions paired with quantitative diagnostics.

Zitieren

APA

Singh, G., & Dhari, R. S. (2026). A framework for visual-mathematical literacy in applied machine learning: why representation choices shape what models can learn. Machine Learning: Engineering, 2(2), 025004. https://doi.org/10.1088/3049-4761/ae7df3

Vancouver

Singh G, Dhari RS. A framework for visual-mathematical literacy in applied machine learning: why representation choices shape what models can learn. Machine Learning: Engineering. 2026;2(2):025004. doi:10.1088/3049-4761/ae7df3

BibTeX
@article{Singh2026,
  author = {Singh, Gaurav and Dhari, Rahul Singh},
  title = {A framework for visual-mathematical literacy in applied machine learning: why representation choices shape what models can learn},
  journal = {Machine Learning: Engineering},
  year = {2026},
  volume = {2},
  number = {2},
  pages = {025004},
  doi = {10.1088/3049-4761/ae7df3}
}
Kostenlos starten →