Artificial intelligence in architecture: Generating conceptual design via deep learning

被引:98
作者
As, Imdat [1 ]
Pal, Siddharth [2 ]
Basu, Prithwish [2 ]
机构
[1] Univ Hartford, Dept Architecture, 200 Bloomfield Ave, Hartford, CT 06117 USA
[2] Raytheon BBN Technol, Cambridge, MA USA
关键词
Architectural design; conceptual design; deep learning; artificial intelligence; generative design;
D O I
10.1177/1478077118800982
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Artificial intelligence, and in particular machine learning, is a fast-emerging field. Research on artificial intelligence focuses mainly on image-, text- and voice-based applications, leading to breakthrough developments in self-driving cars, voice recognition algorithms and recommendation systems. In this article, we present the research of an alternative graph-based machine learning system that deals with three-dimensional space, which is more structured and combinatorial than images, text or voice. Specifically, we present a function-driven deep learning approach to generate conceptual design. We trained and used deep neural networks to evaluate existing designs encoded as graphs, extract significant building blocks as subgraphs and merge them into new compositions. Finally, we explored the application of generative adversarial networks to generate entirely new and unique designs.
引用
收藏
页码:306 / 327
页数:22
相关论文
共 24 条
[1]  
Alexander C., 1977, PATTERN LANGUAGE TOW
[2]  
Boyer J.M., 2004, J COMPUT APPL MATH, V8, P241, DOI DOI 10.7155/JGAA.00091
[3]  
Crosbie M., 2018, FAITH FORUM, V51
[4]  
Cross N., 2011, DESIGN THINKING UNDE
[5]  
de Haan H., 1988, ARCHITECTS COMPETITI
[6]   Towards the mass customization of housing: the grammar of Siza's houses at Malagueira [J].
Duarte, JP .
ENVIRONMENT AND PLANNING B-PLANNING & DESIGN, 2005, 32 (03) :347-380
[7]  
Duvenaud D., 2015, P 28 INT C NEUR INF, V2
[8]   PUSHOUT-PROPERTIES - ANALYSIS OF GLUING CONSTRUCTIONS FOR GRAPHS [J].
EHRIG, H ;
KREOWSKI, HJ .
MATHEMATISCHE NACHRICHTEN, 1979, 91 :135-149
[9]  
Gropius W., 1970, SCOPE TOTAL ARCHITEC
[10]   node2vec: Scalable Feature Learning for Networks [J].
Grover, Aditya ;
Leskovec, Jure .
KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :855-864