Conference Paper

Design-Bot - Using Half-Automated Qualitative Interviews as Part of Self Communication within the Design Process

Authors:
To read the full-text of this research, you can request a copy directly from the author.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the author.

... Besides generative applications, there are alternative studies that use the creative writing method in architectural education to create the design idea and integrate this method to improve the verbal definition of the design through a chat-bot called Nuncias [44]. Conceptual data acquired through this chatbot is then analyzed for a qualitative evaluation of the design process. ...
Full-text available
Article
This work displays an outlook on major questions concerning the integration of Artificial Intelligence (AI) in Architectural education. Gradually, part of the domain knowledge and hard skills become either irrelevant or insufficient by the time the students graduate. This paper suggests that integrating AI in the architectural design curriculum is beneficial for raising designers’ awareness of all areas of architectural design, in the form of input, process, and output. The study views consecutive learning experiences in a continuum and explores the potentials of integrating AI applications and techniques in architectural education, and how architectural design practice may benefit from it. Consequently, it provides insights into how architectural design education may transform itself considering the future impact of AI on the Architecture Engineering Construction (AEC) industry.
... In the architectural field, Gagne et al. [45] applied similar ideas to daylight design, by developing a knowledge-based system that relates performance enhancements with design changes. More recently, Kulcke [46] explored recommender systems' ideas to create a design-bot that iteratively asks questions with the purpose of enhancing selfcommunication, and, thus, clarifying architect's intents. Both works depend on the knowledge that they were initially programmed with, thus, suffering from contextual limitations, making them unable to learn from new unseen designs or to adapt to new trends. ...
Full-text available
Conference Paper
Architecture has always followed and adopted technological breakthroughs of other areas. As a case in point, in the last decades, the field of computation changed the face of architectural practice. Considering the recent breakthroughs of Machine Learning (ML), it is expectable to see architecture adopting ML-based approaches. However, it is not yet clear how much this adoption will change the architectural practice and in order to forecast this change it is necessary to understand the foundations of ML and its impact in other fields of human activity. This paper discusses important ML techniques and areas where they were successfully applied. Based on those examples, this paper forecast hypothetical uses of ML in the realm of building design. In particular, we examine ML approaches in conceptualization, algorithmization, modeling, and optimization tasks. In the end, we conjecture potential applications of such approaches, suggest future lines of research, and speculate on the future face of the architectural profession. 1 Introduction In the last decades, computational advances changed the way architects design. Computation revolutionized architecture and, nowadays, computational approaches are fully embedded in the architectural practice. Recently, a new computational revolution is under way. This revolution is being driven by recent breakthroughs in the area of Machine Learning (ML) [1] and it already affected many fields [2], including medicine [3-4], physics [5], and finance [6], among others. ML is a non-symbolic branch of Artificial Intelligence (AI), based on computational statistics and optimization procedures, that explore self-improving learning techniques to solve problems or perform specific tasks. In contrast to symbolic approaches to AI, non-symbolic approaches strive to build computational systems that do not need to be programmed to perform the task. Particularly, ML builds mathematical models of sampled data, known as training data, and adapts its
... In the architectural field, Gagne et al. [45] applied similar ideas to daylight design, by developing a knowledge-based system that relates performance enhancements with design changes. More recently, Kulcke [46] explored recommender systems' ideas to create a design-bot that iteratively asks questions with the purpose of enhancing selfcommunication, and, thus, clarifying architect's intents. Both works depend on the knowledge that they were initially programmed with, thus, suffering from contextual limitations, making them unable to learn from new unseen designs or to adapt to new trends. ...
Full-text available
Preprint
Architecture has always followed and adopted technological breakthroughs of other areas. As a case in point, in the last decades, the field of computation changed the face of architectural practice. Considering the recent breakthroughs of Machine Learning (ML), it is expectable to see architecture adopting ML-based approaches. However, it is not yet clear how much this adoption will change the architectural practice and in order to forecast this change it is necessary to understand the foundations of ML and its impact in other fields of human activity. This paper discusses important ML techniques and areas where they were successfully applied. Based on those examples, this paper forecast hypothetical uses of ML in the realm of building design. In particular, we examine ML approaches in conceptualization, algorithmization, modeling, and optimization tasks. In the end, we conjecture potential applications of such approaches, suggest future lines of research, and speculate on the future face of the architectural profession.
Article
This article introduces a model for group facilitation in the humanities based on Carl Roger’s model for group psychotherapy. Certain aspects of Carl Roger’s reflective learning strategies are reappraised and principles, specific only to psychotherapy, are introduced. Five of Rogers’s axioms are applied to the tutorial discussion model: a non-directive approach, climate-setting, facilitation, reflective listening and positive regard. The model, which has been trialed in tutorials at The University of Queensland encourages active learning, self-direction and critical thinking.
Chatbots as Interface to Ontologies
  • A Augello
  • G Pilato
  • Vassalo
  • S Gaglio
Augello, A, Pilato, G, Vassalo, G and Gaglio, S 2014, Chatbots as Interface to Ontologies, Springer
Towards an Understanding of Design Tutoring -A grounded study of presentation materials used in tutorial conversations
  • Herr
  • J Karakiewicz
Herr, CM and Karakiewicz, J 2006 'Towards an Understanding of Design Tutoring -A grounded study of presentation materials used in tutorial conversations', CAADRIA Proceedings Mayring, P 2010, 'Qualitative Inhaltsanalyse', in May, G and Mruck, K (eds) 2010, Handbuch Qualitative Forschung in der Psychologie, VS Verlag -Springer Fachmedien, Wiesbaden, pp. 601-613
Helferlein -Der Chatbot Hubot als Dienstleister für alle Lebenslagen
  • Schumacher
Schumacher, M 2017, 'Helferlein -Der Chatbot Hubot als Dienstleister für alle Lebenslagen', c't, 01/2017, p. 139
Knowledge-Based Configuration -From Research to Business Cases
  • J Tiihonen
  • Felfernig
  • M Mandl
Tiihonen, J, Felfernig, A and Mandl, M 2014, 'Personalized Configuration', in Felfernig, A, Hotz, L, Bagley, C and Tiihonen, J (eds) 2014, Knowledge-Based Configuration -From Research to Business Cases, Morgan Kaufmann, Waltham, p. 176
Über Engramme und Exogramme -Die Sozialität des autobiographischen Gedächtnisses
  • J Weizenbaum
Weizenbaum, J 1976, Computer Power and Human Reason -From Judgement to Calculation, W.H.Freeman & Co Ltd, San Francisco Welzer, H 2006, 'Über Engramme und Exogramme -Die Sozialität des autobiographischen Gedächtnisses', in Welzer, H and Markowitsch, HJ (eds) 2006, Warum Menschen sich erinnern können -Fortschritte der interdisziplinären Gedächtnisforschung, Klett-Cotta, Stuttgart, pp. 111-128