Sequencing the Architectural Design Process for Artificial Intelligence - A design-theory-based framework for machine learning approaches

Similar process models of the architectural design process of the early design stages have been formalised. However, recognition by machine learning (ML) based approaches fails due to the individuality and vagueness of the inherent method of sketching. Nevertheless, contemporary ML approaches have the potential to support the architectural design process through auto-completion-based suggestions. In order to provide data for ML-based suggestion generation, we propose a customisable framework with according steps. Drawing from design theory, it is establishes the design process as sequences of three levels of detail and their respective linking. These literature-based sequences serve to label sketch protocol studies. Finally, the framework is validated through Recurrent Neural Networks (RNNs) with Long-Short-Term-Memory (LSTM) architecture trained in isolation on sequences of different level of detail, for prediction purposes.     «

Similar process models of the architectural design process of the early design stages have been formalised. However, recognition by machine learning (ML) based approaches fails due to the individuality and vagueness of the inherent method of sketching. Nevertheless, contemporary ML approaches have the potential to support the architectural design process through auto-completion-based suggestions. In order to provide data for ML-based suggestion generation, we propose a customisable framework wit...     »