Comparative Evaluation of Tensor-based Data Representations for Deep Learning Methods in Architecture

Viktor Eisenstadt, Hardik Arora, Christoph Ziegler, Jessica Bielski, Christoph Langenhan, Klaus-Dieter Althoff, Andreas Dengel

In: V. Stojakovic , B. Tepavcevic (editor). Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 1. Education and Research in Computer Aided Architectural Design in Europe (eCAADe-2021) September 8-10 Novi Sad Serbia Pages 45-54 CUMINCAD 2021.


This paper presents an extended evaluation of tensor-based representations of graph-based architectural room configurations. This experiment is a continuation of examination of recognition of semantic architectural features by contemporary standard deep learning methods. The main aim of this evaluation is to investigate how the deep learning models trained using the relation tensors as data representation means perform on data not available in the training dataset. Using a straightforward classification task, stepwise modifications of the original training dataset and manually created spatial configurations were fed into the models to measure their prediction quality. We hypothesized that the modifications that influence the class label will not decrease this quality, however, this was not confirmed and most likely the latent non-class defining features make up the class for the model. Under specific circumstances, the prediction quality still remained high for the winning relation tensor type.


Weitere Links

ecaade2021_254.pdf (pdf, 819 KB )

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz