CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
References

Hits 1 to 3 of 3

_id cf2019_003
id cf2019_003
authors Steinfeld, Kyle; Katherine Park, Adam Menges and Samantha Walker
year 2019
title Fresh Eyes A framework for the application of machine learning to generative architectural design, and a report of activities at Smartgeometry 2018
source Ji-Hyun Lee (Eds.) "Hello, Culture!"  [18th International Conference, CAAD Futures 2019, Proceedings / ISBN 978-89-89453-05-5] Daejeon, Korea, p. 22
summary This paper presents a framework for the application of Machine Learning (ML) to Generative Architectural Design (GAD), and illustrates this framework through a description of a series of projects completed at the Smart Geometry conference in May of 2018 (SG 2018) in Toronto. Proposed here is a modest modification of a 3-step process that is well-known in generative architectural design, and that proceeds as: generate, evaluate, iterate. In place of the typical approaches to the evaluation step, we propose to employ a machine learning process: a neural net trained to perform image classification. This modified process is different enough from traditional methods as to warrant an adjustment of the terms of GAD. Through the development of this framework, we seek to demonstrate that generative evaluation may be seen as a new locus of subjectivity in design.
keywords Machine Learning, Generative Design, Design Methods
series CAAD Futures
email
last changed 2019/07/29 14:08

_id ecaadesigradi2019_516
id ecaadesigradi2019_516
authors Fioravanti, Antonio and Trento, Armando
year 2019
title Close Future: Co-Design Assistant - How Proactive design paradigm can help
source Sousa, JP, Xavier, JP and Castro Henriques, G (eds.), Architecture in the Age of the 4th Industrial Revolution - Proceedings of the 37th eCAADe and 23rd SIGraDi Conference - Volume 1, University of Porto, Porto, Portugal, 11-13 September 2019, pp. 155-160
doi https://doi.org/10.52842/conf.ecaade.2019.1.155
summary The present paper is focused on exploring a new paradigm in architectural design process that should raise the bar for a mutual collaboration between humans and digital assistants, able to face challenging problems of XXI century. Such a collaboration will aid design process freeing designer from middle level reasoning tasks, so they could focus on exploring - on the fly - design alternatives at a higher abstraction layer of knowledge. Such an assistant should explore and instantiate as much as possible knowledge structures and their inferences thanks to an extensive use of defaults, demons and agents, combined with its power and ubiquity so that they will be able to mimic behaviour of architectural design human experts. It aims other than to deal with data (1st layer) and simple reasoning tools (2nd layer) to automate design exploring consequences and side effects of design decisions and comparing goals (3rd layer). This assistant will speed up the evaluation of fresh design solutions, will suggest solutions by means of generative systems and will be able of a digital creativity.
keywords Design process paradigm; Architectural design; Design assistant; Agents; Knowledge structures
series eCAADeSIGraDi
email
last changed 2022/06/07 07:50

_id caadria2019_183
id caadria2019_183
authors Macken, Marian, Mulla, Sarosh and Paterson, Aaron
year 2019
title Inhabiting the Drawing - 1:1 in time and space
source M. Haeusler, M. A. Schnabel, T. Fukuda (eds.), Intelligent & Informed - Proceedings of the 24th CAADRIA Conference - Volume 1, Victoria University of Wellington, Wellington, New Zealand, 15-18 April 2019, pp. 505-514
doi https://doi.org/10.52842/conf.caadria.2019.1.505
summary One of the fundamental characteristics of architectural drawing is its use of scale. Since the Renaissance - during which architectural production shifted from the construction site to paper - this scalar understanding began by using bodily measurements. In developing designs, the architect projects future occupation of the drawing with their eyes and hands moving over both its physical surface and represented space. The different relationship established between the digital drawer and the body has been criticised; Paul Emmons argues that CAD's full scale - or rather scale-less - capabilities omit this bodily presence of the drawer (Emmons, 2005). Due to the use of full scale data recording, the drawer zooms in and out to consider aspects, severing the drawing's relation to the operator's body. This paper explores ways in which the body and drawings intersect, beyond Emmons definition, and hence considers the influence of the method of drawing on perceptions of scale and the inhabitation of digital drawings. It uses ongoing collaborative research projects and exhibitions to explore the inhabitation of digital drawing at full scale. These works highlight the fundamental importance of the line within architecture, not as demarcation, divider or indexical reference, but as a traces of bodily projections.
keywords architectural drawing; architectural scale; full scale drawing; post factum documentation
series CAADRIA
email
last changed 2022/06/07 07:59

No more hits.

HOMELOGIN (you are user _anon_285512 from group guest) CUMINCAD Papers Powered by SciX Open Publishing Services 1.002