Emmanouil Vermisso · ICCC'20
Deep Learning as heuristic approach for architectural concept generation
This work discusses the use of machine learning for extending the boundaries of architectural concepts. The use of deep learning algorithms is exploited for transferring stylistic attributes from one visual (archi-tectural) domain to another (architectural or other-wise). The combination of various semantic features into hybrid results helps locate possibilities for further exploration of one domain. The process is regarded as open-ended, taking advantage of a generative ad-versarial network’s (cycleGAN) capacity to “imagine” new results which may set the base for new morpho-logical or structural architectural paradigms. We are interested to situate the training results within the con-text of human and computational creativity, embrac-ing the capacity of automated heuristic methods to produce novel outcomes which can augment human decision making in design and architecture.
Multiple speakers · ICCC'20