Re/Learning the Wheel: Methods to Utilize Neural Networks as Design Tools for Doubly Curved Metal Surfaces

Gabriella Rossi, Paul Nicholas

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

48 Downloads (Pure)

Abstract

This paper introduces concepts and computational methodologies for utilizing neural networks as design tools for architecture and demonstrates their application in the making of doubly curved metal surfaces using a contemporary version of the English Wheel. The research adopts an interdisciplinary approach to develop a novel method to model complex geometric features using computational models that originate from the field of computer vision.
The paper contextualizes the approach with respect to the current state of the art of the usage of artificial neural networks both in architecture and beyond. It illustrates the cyber physical system that is at the core of this research, with a focus on the employed neural network–based computational method. Finally, the paper discusses the repercussions of these design tools on the contemporary design paradigm.
Original languageEnglish
Title of host publicationACADIA // 2018: Recalibration. On imprecisionand infidelity : Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture
Number of pages9
Publication dateOct 2019
Pages146-155
ISBN (Electronic)978-0-692-17729-7
Publication statusPublished - Oct 2019
EventACADIA 2018: Recalibration. On imprecision and infidelity - Universidad Iberoamericana, Mexico City, Mexico
Duration: 18 Oct 201820 Oct 2018
http://2018.acadia.org/schedule.html

Conference

ConferenceACADIA 2018
LocationUniversidad Iberoamericana
CountryMexico
CityMexico City
Period18/10/201820/10/2018
Internet address

Keywords

  • machine learning
  • cyber physical systems
  • digital design
  • robotic fabrication

Artistic research

  • No

Cite this

Rossi, G., & Nicholas, P. (2019). Re/Learning the Wheel: Methods to Utilize Neural Networks as Design Tools for Doubly Curved Metal Surfaces. In ACADIA // 2018: Recalibration. On imprecisionand infidelity: Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture (pp. 146-155)
Rossi, Gabriella ; Nicholas, Paul. / Re/Learning the Wheel : Methods to Utilize Neural Networks as Design Tools for Doubly Curved Metal Surfaces. ACADIA // 2018: Recalibration. On imprecisionand infidelity: Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture. 2019. pp. 146-155
@inproceedings{81f0c3cb0a24430bbc4ae71bfeb28db1,
title = "Re/Learning the Wheel: Methods to Utilize Neural Networks as Design Tools for Doubly Curved Metal Surfaces",
abstract = "This paper introduces concepts and computational methodologies for utilizing neural networks as design tools for architecture and demonstrates their application in the making of doubly curved metal surfaces using a contemporary version of the English Wheel. The research adopts an interdisciplinary approach to develop a novel method to model complex geometric features using computational models that originate from the field of computer vision.The paper contextualizes the approach with respect to the current state of the art of the usage of artificial neural networks both in architecture and beyond. It illustrates the cyber physical system that is at the core of this research, with a focus on the employed neural network–based computational method. Finally, the paper discusses the repercussions of these design tools on the contemporary design paradigm.",
keywords = "machine learning, cyber physical systems, digital design, robotic fabrication",
author = "Gabriella Rossi and Paul Nicholas",
year = "2019",
month = "10",
language = "English",
pages = "146--155",
booktitle = "ACADIA // 2018: Recalibration. On imprecisionand infidelity",

}

Rossi, G & Nicholas, P 2019, Re/Learning the Wheel: Methods to Utilize Neural Networks as Design Tools for Doubly Curved Metal Surfaces. in ACADIA // 2018: Recalibration. On imprecisionand infidelity: Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture. pp. 146-155, ACADIA 2018, Mexico City, Mexico, 18/10/2018.

Re/Learning the Wheel : Methods to Utilize Neural Networks as Design Tools for Doubly Curved Metal Surfaces. / Rossi, Gabriella; Nicholas, Paul.

ACADIA // 2018: Recalibration. On imprecisionand infidelity: Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture. 2019. p. 146-155.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - Re/Learning the Wheel

T2 - Methods to Utilize Neural Networks as Design Tools for Doubly Curved Metal Surfaces

AU - Rossi, Gabriella

AU - Nicholas, Paul

PY - 2019/10

Y1 - 2019/10

N2 - This paper introduces concepts and computational methodologies for utilizing neural networks as design tools for architecture and demonstrates their application in the making of doubly curved metal surfaces using a contemporary version of the English Wheel. The research adopts an interdisciplinary approach to develop a novel method to model complex geometric features using computational models that originate from the field of computer vision.The paper contextualizes the approach with respect to the current state of the art of the usage of artificial neural networks both in architecture and beyond. It illustrates the cyber physical system that is at the core of this research, with a focus on the employed neural network–based computational method. Finally, the paper discusses the repercussions of these design tools on the contemporary design paradigm.

AB - This paper introduces concepts and computational methodologies for utilizing neural networks as design tools for architecture and demonstrates their application in the making of doubly curved metal surfaces using a contemporary version of the English Wheel. The research adopts an interdisciplinary approach to develop a novel method to model complex geometric features using computational models that originate from the field of computer vision.The paper contextualizes the approach with respect to the current state of the art of the usage of artificial neural networks both in architecture and beyond. It illustrates the cyber physical system that is at the core of this research, with a focus on the employed neural network–based computational method. Finally, the paper discusses the repercussions of these design tools on the contemporary design paradigm.

KW - machine learning

KW - cyber physical systems

KW - digital design

KW - robotic fabrication

M3 - Article in proceedings

SP - 146

EP - 155

BT - ACADIA // 2018: Recalibration. On imprecisionand infidelity

ER -

Rossi G, Nicholas P. Re/Learning the Wheel: Methods to Utilize Neural Networks as Design Tools for Doubly Curved Metal Surfaces. In ACADIA // 2018: Recalibration. On imprecisionand infidelity: Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture. 2019. p. 146-155