Reconstructing Abstract Concepts and their Blends Via Computational Cognitive Modeling



Concept Blending is one of the most prominent computational approaches to study and understand the underlying processes related to creativity. In this article, we show how to use the Regulated Activation Network (RAN) cognitive model to reconstruct abstract concepts and their blends. The MNIST dataset is used in this work to build a representation of abstract concepts. For the demonstration, three experiments were designed: first, shows how a high dimensional input image is encoded into a low dimension vector and further reconstructed back into an image; second, reconstruction of blends of abstract concepts that represent same digits; third, reconstructing blends of abstract concepts which represent different digits. The reconstructed images in all three experiments were visually analyzed. The best reconstructions were observed with the encoded image experiment obtaining Mean Squared Error of 0.00562 and an R-square score of 0.9193. The blends of similar abstract concepts also reconstructed the expected blend of a digit. The blends of dis-similar abstract concepts reconstructed the images by creating interesting symbols such as character x.


Computational Creativity, Concept Blending, Dimension Reduction, Concept Reconstruction, Computational Modeling


Computation Cognitive Modeling


International Joint Conference on Neural Network, July 2020

Cited by

No citations found