Fig 4 - uploaded by Andrzej Tuchołka
Content may be subject to copyright.
Source publication
Proposed method allows for early detection of mistakes in designs of mechanical constructions. It is based on a numerical classification of a symbolic representation of construction’s features against a set of defined antipatterns (known, incorrect, repeatable data patterns). We present an approach to identify antipatterns described using a symboli...
Context in source publication
Context 1
... is important to highlight the difference between the positive correlation occurring in when classifying against a correct dataset, from the negative one when comparing against antipatterns (Fig. 4.). This can lead to further improvements in quality interpretation, by adding weighed grade of similarity to correct designs. In the presented method (Fig. 5.) the input data contains a matrix of feature values, accompanied by a numerical representation of node class structure. Such model, allows to generate network activation based on ...
Similar publications
Deep learning (DL) from various representations have succeeded in many fields. However, we know little about the machine learnability of distinct design representations when using DL to predict design performance. This paper proposes a graph representation for designs and compares it to the common image representation. We employ graph neural networ...
