Using Recurrent Neural Networks to Model Spatial Grammars for Design Creation

The authors present preliminary results on successfully training a recurrent neural network to learn a spatial grammar embodied in a data set, and then generate new designs that comply with the grammar but are not from the data set, demonstrating generalized learning. For the test case, the data wer...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of mechanical design (1990) 2020-10, Vol.142 (10), Article 104501
Hauptverfasser:	Yukish, Michael A, Stump, Gary M, Miller, Simon W
Format:	Artikel
Sprache:	eng
Schlagworte:	Engineering Engineering, Mechanical Science & Technology Technology
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!