From shape grammars to machine learning: a plea for the neuro-symbolic approach to generative AI
Architectural Intelligence · 13.08.2026 · 5 (1)
DOI: 10.1007/s44223-026-00129-3 ↗Kurz gefasst
Fachartikel in der Zeitschrift Architectural Intelligence, online erschienen am 13.08.2026. Verfasst von Mario Carpo. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
A comparison between examples of style transfer and stylistic imitation as envisaged by the theory of Shape Grammars in the 1970s and those enabled by Generative AI today (with case studies and student work from a research seminar). The essay emphasizes the limits of Generative AI as a pure imitation machine, and argues for a merger of old-school rule-based systems and contemporary LLM-based machine learning.
Zitieren
APA
Carpo, M. (2026). From shape grammars to machine learning: a plea for the neuro-symbolic approach to generative AI. Architectural Intelligence, 5(1). https://doi.org/10.1007/s44223-026-00129-3
Vancouver
Carpo M. From shape grammars to machine learning: a plea for the neuro-symbolic approach to generative AI. Architectural Intelligence. 2026;5(1). doi:10.1007/s44223-026-00129-3
BibTeX
@article{Carpo2026,
author = {Carpo, Mario},
title = {From shape grammars to machine learning: a plea for the neuro-symbolic approach to generative AI},
journal = {Architectural Intelligence},
year = {2026},
volume = {5},
number = {1},
doi = {10.1007/s44223-026-00129-3}
}
EUVIMED