Cumincad : CUMINCAD Papers : Search Results

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 20 of 342

Reformat results as: short short into frame detailed detailed into frame

_id	2475
authors	Asimov, Isaac
year	1968
title	The Perfect Machine
source	Science Journal October, 1968. pp. 115-118 : ill.
summary	The author takes a semi-serious look at the world of computers, robots and androids in an attempt to find a recipe for the perfect machine. Described in this article are the possible attributes of the perfect machine and some of the problems it might raise
keywords	robotics, science fiction
series	CADline
last changed	1999/02/12 15:07

_id	5cf4
id	5cf4
authors	Barrionuevo, Luis F.
year	2004
title	LOS "SPIROSPACES"
source	Proceedings of the Fourth International Conference of Mathematics & Design, Special Edition of the Journal of Mathematics & Design, Volume 4, No.1, pp. 179-187.
summary	This paper deals with “Spirospaces”. These are a conversion to the third dimension of the two dimensional geometric entities called “Spirolaterals”. Abelson, Harold, diSessa and Andera (1968) gave the first rules concerning Spirolaterals. To obtain a Spirolateral from a set of straight lines, the first of them must be one unit long and the following must be incremented one unit at each step, at the same time that they turn in a constant direction. Odds (1973) establish the variation of the rotation direction, either to the left or the right. However, he did not give a mathematical relation able to calculate open Spirolaterals. Krawczyk (2001) developed a computer program that generates Spirolaterals following the method suggested by Abelson. These are Spirolaterals obtained by enumeration without a predictive mathematical formula. Krawczyc went farther proposing Spirolaterals based in curved lines. He pointed out that there are a variety of spirolateral forms that have architectural potentiality. Following this, the architectural potentiality of Spirolaterals is the basis of this paper. To take advantage of that potentiality a computer program was implemented to generate spatial configurations based in Spirolaterals. When a third dimension is given to the Spirolaterals they become Spirospaces. These new entities need spatial and design parameters to be useful for architectural purposes. Barrionuevo and Borsetti (2001) gave results about that work establishing the concept of Spirospaces. The aim of this paper is to describe a work directed to improve rules and procedures concerning Spirospaces. It is expected that these procedures governed by the proposed rules can be employed as tools during the early steps in the architectural design process. In this work some aspects concerning Spirospaces are considered. First, Spirolaterals are presented as the predecessors of Spirospaces. Second, Spirospaces are defined, together with their structural parameters. Architectural modeling is studied at the light of two special elements of the Spirospaces: Interstitial spaces and Object spaces. Next, a computer program is presented as the appropriate tool to model configurations having architectural potentiality. Finally, the results obtained running the computer program are analyzed to determine their possible use as architectural forms. Several graphic illustrations are presented showing steps going from the exploration of spatial alternatives to the selection of a specific configuration to be developed. It is expected that the described computer program could be employed as a design aid tool. As the operation of the program generates a variety of spaces able to dwell architectural objects, it eases the search of configurations suitable to specific functions. The results obtained have the possibility of being exported to computer graphic applications able to add materials, lights and cameras.
keywords	Spirolaterals, Spirospaces, architectural spaces, interstitial spaces, objectual spaces
series	other
type	normal paper
email
last changed	2005/04/07 15:34

_id	caadria2022_507
id	caadria2022_507
authors	Bolojan, Daniel, Vermisso, Emmanouil and Yousif, Shermeen
year	2022
title	Is Language All We Need? A Query Into Architectural Semantics Using a Multimodal Generative Workflow
doi	https://doi.org/10.52842/conf.caadria.2022.1.353
source	Jeroen van Ameijde, Nicole Gardner, Kyung Hoon Hyun, Dan Luo, Urvi Sheth (eds.), POST-CARBON - Proceedings of the 27th CAADRIA Conference, Sydney, 9-15 April 2022, pp. 353-362
summary	This project examines how interconnected artificial intelligence (AI)-assisted workflows can address the limitations of current language-based models and streamline machine-vision related tasks for architectural design. A precise relationship between text and visual feature representation is problematic and can lead to "ambiguity‚ in the interpretation of the morphological/tectonic complexity of a building. Textual representation of a design concept only addresses spatial complexity in a reductionist way, since the outcome of the design process is co-dependent on multiple interrelated systems, according to systems theory (Alexander 1968). We propose herewith a process of feature disentanglement (using low level features, i.e., composition) within an interconnected generative adversarial networks (GANs) workflow. The insertion of natural language models within the proposed workflow can help mitigate the semantic distance between different domains and guide the encoding of semantic information throughout a domain transfer process.
keywords	Neural Language Models, GAN, Domain Transfer, Design Agency, Semantic Encoding, SDG 9
series	CAADRIA
email
last changed	2022/07/22 07:34

_id	82cd
authors	Comba, Paul G.
year	1968
title	A Procedure for Detecting Intersections of Three-Dimensional Objects
source	Journal of the Association for Computing Machinery. July, 1968. vol. 15: pp. 354-366 ; ill. includes bibliography
summary	As a step toward the solution of the placement problem in engineering design, a procedure has been developed for detecting intersections of convex regions in 3-space by means of a pseudocharacteristic function. The mathematical techniques underlying the procedure are discussed, and a system of programs embodying these techniques is described. As a special case a solution is given for the hidden-line problem in graphic display
keywords	intersection, interference, engineering, design, modeling, computer graphics, hidden lines, computational geometry, algorithms
series	CADline
last changed	2003/06/02 13:58

_id	273f
authors	Elcock, E.W.
year	1983
title	How Complete are Knowledge Representation Systems?
source	IEEE Computer. IEEE computer society, October, 1983. vol. 16: pp. 114-118. includes bibliography
summary	Prolog, the most feasible of the first-order logic systems, has intriguing analogies with Absys, short for Aberdeen System, an assertative programming system developed in 1968. In this article, the issue of incompleteness is explored by comparing aspects of the two systems, and the incompleteness resulting from any serious use of Prolog as a vehicle for a knowledge-based system is addressed
keywords	PROLOG, algorithms, knowledge, systems, languages
series	CADline
last changed	2003/06/02 13:58

_id	caadria2012_089
id	caadria2012_089
authors	Fernando, R.; R. Drogemuller and A. Burden
year	2012
title	Parametric and generative methods with building information modelling: Connecting BIM with explorative design modelling
doi	https://doi.org/10.52842/conf.caadria.2012.537
source	Proceedings of the 17th International Conference on Computer Aided Architectural Design Research in Asia / Chennai 25-28 April 2012, pp. 537–546
summary	Parametric and generative modelling methods are ways in which computer models are made more flexible, and of formalising domain-specific knowledge. At present, no open standard exists for the interchange of parametric and generative information. The Industry Foundation Classes (IFC) which are an open standard for interoperability in building information models is presented as the base for an open standard in parametric modelling. The advantage of allowing parametric and generative representations are that the early design process can allow for more iteration and changes can be implemented quicker than with traditional models. This paper begins with a formal definition of what constitutes to be parametric and generative modelling methods and then proceeds to describe an open standard in which the interchange of components could be implemented. As an illustrative example of generative design, Frazer’s ‘Reptiles’ project from 1968 is reinterpreted.
keywords	Building information model; parametric modelling; generative modelling
series	CAADRIA
email
last changed	2022/06/07 07:51

_id	ga0202
id	ga0202
authors	Frazer, Jh., Frazer, J., Liu X., Tang M. and Janssen, P.
year	2002
title	Generative and Evolutionary Techniques for Building Envelope Design
source	International Conference on Generative Art
summary	The authors have been involved in the use of generative techniques for building envelope design since 1968 and the use of genetic algorithms since 1990. Recent work has focused on incorporating optimisation functions into form generating processes in order for new forms responding to varied design environments to be created and determined. This paper will summarise the authors’ previous work in this field and explain the theory behind this approach, and illustrate recent developments. While the initial implementation of a new building envelope design system is reported in more details in a related paper at this conference, this paper outlines its main features and points out the direction at which it is to be fully developed and further improved.
series	other
email
more	http://www.generativeart.com/
last changed	2003/08/07 17:25

_id	ascaad2023_032
id	ascaad2023_032
authors	Kalak, Dogan; Aydin, Serdar; Özer, Derya
year	2023
title	Use of Generative Systems to Create Semi-Public Spaces in Contemporary Neighborhood Texture
source	C+++: Computation, Culture, and Context – Proceedings of the 11th International Conference of the Arab Society for Computation in Architecture, Art and Design (ASCAAD), University of Petra, Amman, Jordan [Hybrid Conference] 7-9 November 2023, pp. 306-323.
summary	Cul-de-sacs are examined together with the urban reading in Siverek. Studying cul-de-sacs is instrumental to understand the morphology of Islamic cities. Cul-de-sacs provide a buffer zone between main roads and houses. For this reason, both the privacy phenomenon, which is one of the important issues for Islam, and the safe space need of the residents are important spatial elements. Until 1968, the city of Siverek developed organically within a compact texture of narrow and curvilinear streets, open courtyards, and a adjacent high-walled residences. In this texture, many semi-private cul-de-sacs have an organic form, which is one of the critical spatial elements of the city. Residential walls or courtyard walls form the natural line of traditional streets. In this study, typological analyses of cul-de-sacs were made, and form grammar, a productive method used to analyze architectural language, is included. It aims to examine the relationship between residential settlement and street using the data set created with shape grammars and to make urban propositions for neighbourhood structures in the context of a cul-de-sac using L-systems in the next step. Some parameters have been determined in forming cul-de-sacs that form the urban texture. These parameters were transferred to the model using digital tools. A method thought to be used in urban production has been put forward. The most important reference of this method is dead-end streets.
series	ASCAAD
email
last changed	2024/02/13 14:34

_id	caadria2009_026
id	caadria2009_026
authors	Ostwald, Michael J.; Josephine Vaughan
year	2009
title	Calculating Visual Complexity In Peter Eisenman’s Architecture
doi	https://doi.org/10.52842/conf.caadria.2009.075
source	Proceedings of the 14th International Conference on Computer Aided Architectural Design Research in Asia / Yunlin (Taiwan) 22-25 April 2009, pp. 75-84
summary	This paper describes the results of the first computational investigation of characteristic visual complexity in the architecture of Peter Eisenman. The research uses a variation of the “box-counting” approach to determining a quantitative value of the formal complexity present in five of Eisenman’s early domestic works (Houses I, II, III, IV and VI all of which were completed between 1968 and 1976). The boxcounting approach produces an approximate fractal dimension calculation for the visual complexity of an architectural elevation. This method has previously been used to analyse a range of historic and modern buildings including the works of Frank Lloyd Wright, Eileen Gray, Le Corbusier and Kazuyo Sejima. Peter Eisenman’s early house designs–important precursors to his later Deconstructivist works–are widely regarded as possessing a high degree of formal consistency and a reasonably high level of visual complexity. Through this analysis it is possible to quantify both the visual complexity and the degree of consistency present in this work for the first time.
keywords	Computational analysis; fractal dimension; box-counting; Peter Eisenman
series	CAADRIA
email
last changed	2022/06/07 08:00

_id	2005_615
id	2005_615
authors	Serrato-Combe, Antonio
year	2005
title	Lindenmayer Systems – Experimenting with Software String Rewriting as an Assist to the Study and Generation of Architectural Form
doi	https://doi.org/10.52842/conf.ecaade.2005.615
source	Digital Design: The Quest for New Paradigms [23nd eCAADe Conference Proceedings / ISBN 0-9541183-3-2] Lisbon (Portugal) 21-24 September 2005, pp. 615-621
summary	In 1968 Aristid Lindenmayer proposed a series of mathematical constructs as a foundation for an axiomatic theory of form development. Since that time, Lindenmayer Systems or L-systems have evolved and found many practical applications in the computer visualization area. Generation of fractal imagery, realistic modeling and high quality visualization of organic forms and even music generation are now possible with the assistance of L-systems. But, is it possible to use L-systems in architectural design? Why would anyone use L-systems in architectural design? How would one use them? What could one expect from their use? In addition to providing answers to the above questions this paper presents: 1. Concepts behind L-systems 2. The need to transform L-Systems so they can have creative architectural application possibilities 3. Examples on the architectural use of L-Systems 4. Conclusions
keywords	Form Generation, Lindenmayer, String rewriting, Visualization
series	eCAADe
email
last changed	2022/06/07 07:56

_id	sigradi2005_161
id	sigradi2005_161
authors	Serrato-Combe, Antonio
year	2005
title	Lindenmayer Systems – Experimenting with Software String Rewriting as an Assist to the Study and Generation of Architectural Form
source	SIGraDi 2005 - [Proceedings of the 9th Iberoamerican Congress of Digital Graphics] Lima - Peru 21-24 november 2005, vol. 1, pp. 161-166
summary	In 1968 Aristid Lindenmayer proposed a series of mathematical constructs as a foundation for an axiomatic theory of form development. Since that time, Lindenmayer Systems or L-systems have evolved and found many practical applications in the computer visualization area. Generation of fractal imagery, realistic modeling and high quality visualization of organic forms and even music generation are now possible with the assistance of L-systems. But, is it possible to use L-systems in architectural design? Why would anyone use L-systems in architectural design? How would one use them? What could one expect from their use?
series	SIGRADI
type	normal paper
email
last changed	2016/03/10 10:00

_id	8245
authors	Shaviv, Edna and Greenberg, Donald P.
year	1968
title	Funicular Surface Structures: a Computer Graphics Approach
source	Bulletin of the International Association for Shell Structures. Madrid, Spain: 1968. pp. 15-26 : ill. includes some bibliographical notes
summary	This paper describes the problem of finding the shape of the middle surface of a shell when the loading and the stress resultants distributions are known. Differential equations are set up and solved using the finite difference technique. Several solutions are presented by means of an electronic computer and a plotter
keywords	curved surfaces, structures, synthesis, architecture, computer graphics, algorithms
series	CADline
email
last changed	2003/06/02 13:58

_id	caadria2006_633
id	caadria2006_633
authors	WAN-YU LIU
year	2006
title	THE EMERGING DIGITAL STYLE: Attention shift in architectural style recognition
doi	https://doi.org/10.52842/conf.caadria.2006.x.g4f
source	CAADRIA 2006 [Proceedings of the 11th International Conference on Computer Aided Architectural Design Research in Asia] Kumamoto (Japan) March 30th - April 2nd 2006, 633-635
summary	“Style” has long been an important index to observe the design thinking of designers in architecture. Gombrich (1968) defined style as a particular selection from the alternatives when doing things; Ackerman (1963) considered that a distiguishable ensemble of certain characteristics we call a style; Schapiro (1961) pointed out that style is constant forms, and sometimes the constant elements, qualities and expression; Kirsch (1998), Cha and Gero (1999) thought of style as a form element and shape pattern. As Simon and others referred to, style emerged from the process of problem solving, Chan (1994, 2001) ever devised a serious of experiments to set up the operational definitions of style, further five factors that relate to generating styles. Owing to that the greater part of sketches and drawings in the design process couldn’t be replaced by computer-aided design systems (Eisentraut, 1997), designers must shift between different problem-solving methods while facing different design problems. The purpose in this research is to discuss the influences of computer usage on style generation and style recognition: The employment of certain procedural factors that occurred in the design processes that using conventional media is different from the ones that using computer media? Do personal styles emerge while designers shifting between different media in the design processes? Does any unusual phenomenon emerge while accustomed CAD-systems designers recognizing a style?
series	CAADRIA
email
last changed	2022/06/07 07:49

_id	ascaad2004_paper11
id	ascaad2004_paper11
authors	Abdelfattah, Hesham Khairy and Ali A. Raouf
year	2004
title	No More Fear or Doubt: Electronic Architecture in Architectural Education
source	eDesign in Architecture: ASCAAD's First International Conference on Computer Aided Architectural Design, 7-9 December 2004, KFUPM, Saudi Arabia
summary	Operating electronic and Internet worked tools for Architectural education is an important, and merely a prerequisite step toward creating powerful tele-collabortion and tele-research in our Architectural studios. The design studio, as physical place and pedagogical method, is the core of architectural education. The Carnegie Endowment report on architectural education, published in 1996, identified a comparably central role for studios in schools today. Advances in CAD and visualization, combined with technologies to communicate images, data, and “live” action, now enable virtual dimensions of studio experience. Students no longer need to gather at the same time and place to tackle the same design problem. Critics can comment over the network or by e-mail, and distinguished jurors can make virtual visits without being in the same room as the pin-up—if there is a pin-up (or a room). Virtual design studios (VDS) have the potential to support collaboration over competition, diversify student experiences, and redistribute the intellectual resources of architectural education across geographic and socioeconomic divisions. The challenge is to predict whether VDS will isolate students from a sense of place and materiality, or if it will provide future architects the tools to reconcile communication environments and physical space.
series	ASCAAD
email
last changed	2007/04/08 19:47

_id	ecaade2015_324
id	ecaade2015_324
authors	Abdelmohsen, Sherif and Massoud, Passaint
year	2015
title	Integrating Responsive and Kinetic Systems in the Design Studio: A Pedagogical Framework
doi	https://doi.org/10.52842/conf.ecaade.2015.2.071
source	Martens, B, Wurzer, G, Grasl T, Lorenz, WE and Schaffranek, R (eds.), Real Time - Proceedings of the 33rd eCAADe Conference - Volume 2, Vienna University of Technology, Vienna, Austria, 16-18 September 2015, pp. 71-80
summary	Responsive architecture is one of the growing areas of computational design that is not getting adequate attention in CAAD curricula. A pedagogical approach to designing responsive systems requires more than the typical knowledge, tools or skill sets in architectural design studios. This paper presents a framework for integrating responsive and kinetic systems in the architectural design studio. The framework builds on findings of two design studios conducted at The American University in Cairo, Egypt. In both studios, students were asked to design elements of responsive architecture that work towards the development of their projects. The paper demonstrates the process and outcomes of both studios. It then demonstrates how concepts of integrated project delivery are incorporated to propose a framework that engages students in designing, fabricating and operating responsive systems in different phases of the design process. A discussion follows regarding dynamics of design studio in light of the proposed framework.
wos	WOS:000372316000010
series	eCAADe
email
more	https://mh-engage.ltcc.tuwien.ac.at/engage/ui/watch.html?id=7e59e026-6e8f-11e5-9e59-876225eebea0
last changed	2022/06/07 07:54

_id	sigradi2013_215
id	sigradi2013_215
authors	Abdelmohsen, Sherif M.
year	2013
title	Reconfiguring Architectural Space using Generative Design and Digital Fabrication: A Project Based Course
source	SIGraDi 2013 [Proceedings of the 17th Conference of the Iberoamerican Society of Digital Graphics - ISBN: 978-956-7051-86-1] Chile - Valparaíso 20 - 22 November 2013, pp. 391 - 395
summary	This paper discusses a course that addresses the integration between generative design and digital fabrication in the context of reconfiguring architectural space. The objective of the course, offered for 3rd year architecture students at the Department of Architecture, Ain Shams University, Egypt, was to design and fabricate interior design elements to be installed within the department lobby. Students worked in digital and physical environments to develop 8 group projects that featured concepts of shape grammars, L-systems, fractals and cellular automata. The potential of the realized projects is discussed in terms of 3D development of systems, contextual generative design, and pedagogical objectives.
keywords	Contextual generative design; Rule-based systems; Self-organizing systems; Digital fabrication
series	SIGRADI
email
last changed	2016/03/10 09:47

_id	e336
authors	Achten, H., Roelen, W., Boekholt, J.-Th., Turksma, A. and Jessurun, J.
year	1999
title	Virtual Reality in the Design Studio: The Eindhoven Perspective
doi	https://doi.org/10.52842/conf.ecaade.1999.169
source	Architectural Computing from Turing to 2000 [eCAADe Conference Proceedings / ISBN 0-9523687-5-7] Liverpool (UK) 15-17 September 1999, pp. 169-177
summary	Since 1991 Virtual Reality has been used in student projects in the Building Information Technology group. It started as an experimental tool to assess the impact of VR technology in design, using the environment of the associated Calibre Institute. The technology was further developed in Calibre to become an important presentation tool for assessing design variants and final design solutions. However, it was only sporadically used in student projects. A major shift occurred in 1997 with a number of student projects in which various computer technologies including VR were used in the whole of the design process. In 1998, the new Design Systems group started a design studio with the explicit aim to integrate VR in the whole design process. The teaching effort was combined with the research program that investigates VR as a design support environment. This has lead to increasing number of innovative student projects. The paper describes the context and history of VR in Eindhoven and presents the current set-UP of the studio. It discusses the impact of the technology on the design process and outlines pedagogical issues in the studio work.
keywords	Virtual Reality, Design Studio, Student Projects
series	eCAADe
email
last changed	2022/06/07 07:54

_id	7e52
authors	Achten, Henri
year	2001
title	Normative Positions in Architectural Design - Deriving and Applying Design Methods
doi	https://doi.org/10.52842/conf.ecaade.2001.263
source	Architectural Information Management [19th eCAADe Conference Proceedings / ISBN 0-9523687-8-1] Helsinki (Finland) 29-31 August 2001, pp. 263-268
summary	This paper presents a recently finished course of eight weeks where CAAD skills, design methodology, and architectural theory are combined to discuss possible perspectives on the use of the computer in design, and its influence on architecture. In the course, three contemporary architects were studied; Peter Eisenman, Ben van Berkel, and Greg Lynn. Each was discussed on aspects of ontology (which are the elements of discourse), design method (design process and organization of the process), and the use of the computer (techniques and approaches). These were linked with design theory, architectural theory, and CAD-theory. The reflection on the work of the architects resulted in a number of design methods for each architect. The design methods were adapted to the available technologies in the university as well as to the scope of the exercise, since the period of eight weeks for an exercise cannot compete with design processes in practice that take many participants and much time. The students then applied the design methods to a design task: student housing and an exhibition pavilion on the campus area of the university. The task was so devised, that students could focus on either architectural or urban design level with one of the design methods. Also, the choice of architects and accompanying design methods was made in such a way that students with low, medium, and advanced computer skills could take part in the course and exercise. In a workshop held at the Czech Technical University (CVUT) in Prague, the same procedure was used in a one-week period for a different design task, but in an otherwise almost identical setting with respect to the CAAD software used. The methods and material were easily transferred to the other setting. The students were able to cope with the task and produced surprising results in the short time span available. The paper will provide an overview of the course, discuss the pedagogical implications of the work, and discuss how this particular work can be generalized to incorporate other architects and approaches.
keywords	CAAD: Design Methods, Pedagogy
series	eCAADe
email
last changed	2022/06/07 07:54

_id	db60
authors	Af Klercker, J., Achten, H. and Verbeke, J.
year	2001
title	AVOCAAD - A First Step Towards Distance Learning?
doi	https://doi.org/10.52842/conf.ecaade.2001.269
source	Architectural Information Management [19th eCAADe Conference Proceedings / ISBN 0-9523687-8-1] Helsinki (Finland) 29-31 August 2001, pp. 269-274
summary	In the industrial world knowledge is developed very fast. As most countries are depending on employees with a high level of knowledge and skills the term ”Life Long Learning” has been formulated and the concept is more and more accepted. Institutions of higher education are more and more involved in creating supplementary education more independent of time and place. Distance learning was originally carried out by ordinary mail, which was slow but might then have been the only solution for people in remote places. With the Internet and e-mail the distance-learning concept has got a far better tool, for instance better interaction facilities. Architects and engineers in practise are deeply involved in solving the problems of the present projects. Education which is independent of time and place must be of great interest to both parties. The AVOCAAD project has created an education model for students to meet the possibilities of CAAD. The education model can be used in a curriculum at a school as well as for distance learning. Among the possible experiences from it, the one concerning distance learning might be the most important future application of the system in architectural education. This paper sketches the pedagogical background and gives examples from other areas of knowledge, where distance learning is already in use. We will put the question how the AVOCAAD concept meets the experiences from distance learning.
keywords	Distance Learning, Pedagogic, CAAD, E-Learning, AVOCAAD
series	eCAADe
email
last changed	2022/06/07 07:54

_id	ecaade2022_270
id	ecaade2022_270
authors	Akcay Kavakoglu, Aysegul, Almac, Bihter, Eser, Begum and Alacam, Sema
year	2022
title	AI Driven Creativity in Early Design Education - A pedagogical approach in the age of Industry 5.0
doi	https://doi.org/10.52842/conf.ecaade.2022.1.133
source	Pak, B, Wurzer, G and Stouffs, R (eds.), Co-creating the Future: Inclusion in and through Design - Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022) - Volume 1, Ghent, 13-16 September 2022, pp. 133–142
summary	This study presents a pedagogical experiment on the integration of AI into the project studio in the early stages of design education. The motivation of the study is to support creative encounters in design studios by promoting student-design representation, student-student, and student-artificial intelligence (AI) interaction. In the scope of this study, a short-term studio project is used as a case study to examine these creative encounters. The experiment covers five stages that enable a recursive analysis-synthesis action. The stages include (i) precedent analysis of a given set of building façades images, (ii) feature extraction, (iii) composing new façade representations through employing previously generated features, (iv) training an AI by the use of styleGAN2-ADA with the outcomes of stage 3, (v) Use of synthetically generated façade images as a design driver. The pedagogical experiment is evaluated through the lenses of novelty, style, surprisingness, and complexity concepts. The challenges and potentials are introduced, as well as elaborations on the future directions of the interplay between AI-oriented making and first-year student making.
keywords	Artificial Intelligence, Computational Creativity, Design Education, StyleGAN2-ADA
series	eCAADe
email
last changed	2024/04/22 07:10

For more results click below: