Application of Deep Learning in Generating Desired Design Options: Experiments Using Synthetic Training Dataset

Most design methods contain a forward framework, asking for primary specifications of a building to generate an output or assess its performance. However, architects urge for specific objectives though uncertain of the proper design parameters. Deep Learning (DL) algorithms provide an intelligent workflow in which the system can learn from sequential training experiments. This study applies a method using DL algorithms towards generating demanded design options. In this study, an object recognition problem is investigated to initially predict the label of unseen sample images based on training dataset consisting of different types of synthetic 2D shapes; later, a generative DL algorithm is applied to be trained and generate new shapes for given labels. In the next step, the algorithm is trained to generate a window/wall pattern for desired light/shadow performance based on the spatial daylight autonomy (sDA) metrics. The experiments show promising results both in predicting unseen sample shapes and generating new design options.

[1]  Stephen V. Stehman,et al.  Selecting and interpreting measures of thematic classification accuracy , 1997 .

[2]  John Harding,et al.  Associative Spatial Networks in Architectural Design: Artificial Cognition of Space Using Neural Networks with Spectral Graph Theory , 2010, DCC.

[3]  Farshad Kheiri,et al.  A review on optimization methods applied in energy-efficient building geometry and envelope design , 2018, Renewable and Sustainable Energy Reviews.

[4]  David Rutten,et al.  Galapagos: On the Logic and Limitations of Generic Solvers , 2013 .

[5]  Jin Shang,et al.  REGRESSION-BASED BUILDING ENERGY PERFORMANCE ASSESSMENT USING BUILDING INFORMATION MODEL (BIM) , 2016 .

[6]  Wei Yan,et al.  Optimo: A BIM-based Multi-Objective Optimization Tool Utilizing Visual Programming for High Performance Building Design , 2015, eCAADe proceedings.

[7]  David W. Newton,et al.  Generative Deep Learning in Architectural Design , 2019, Technology|Architecture + Design.

[8]  Kari Alanne,et al.  A multi-objective life cycle approach for optimal building design: A case study in Finnish context , 2017 .

[9]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[10]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[11]  Giovanni Zemella,et al.  Optimised design of energy efficient building faades via Evolutionary Neural Networks , 2011 .

[12]  Klaus Bollinger,et al.  ACCOMMODATING CHANGE IN PARAMETRIC DESIGN , 2014 .

[13]  C. H. Antunes,et al.  Clustering of architectural floor plans: A comparison of shape representations , 2017 .

[14]  Mohamed El Mankibi,et al.  Development of a multicriteria tool for optimizing the renovation of buildings , 2011 .

[15]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[16]  Ahmed M. Elgammal,et al.  CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms , 2017, ICCC.

[17]  Ralph Evins,et al.  A review of computational optimisation methods applied to sustainable building design , 2013 .

[18]  Gaurav S. Sukhatme,et al.  Generation of energy efficient trajectories for NIMS3D, a three-dimensional cabled robot , 2008, 2008 IEEE International Conference on Robotics and Automation.

[19]  Wei Yan,et al.  Towards Multi-Objective Optimization for Sustainable Buildings with Both Quantifiable and Non-Quantifiable Design Objectives , 2015 .

[20]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[21]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[22]  Yi-Hsuan Yang,et al.  MidiNet: A Convolutional Generative Adversarial Network for Symbolic-Domain Music Generation , 2017, ISMIR.

[23]  Christiane M. Herr,et al.  Teaching Generative Design , 2001 .

[24]  Jason Brown,et al.  A new approach to performance-based building design exploration using linear inverse modeling , 2018, Journal of Building Performance Simulation.

[25]  Ruslan Salakhutdinov,et al.  Learning Deep Generative Models , 2009 .

[26]  Trevor J. M. Bench-Capon,et al.  Accommodating change , 2016, Artificial Intelligence and Law.

[27]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[28]  Luisa Caldas,et al.  Generation of energy-efficient architecture solutions applying GENE_ARCH: An evolution-based generative design system , 2008, Adv. Eng. Informatics.

[29]  Prithwish Basu,et al.  Artificial intelligence in architecture: Generating conceptual design via deep learning , 2018, International Journal of Architectural Computing.

[30]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.