Grounding Psychological Shape Space in Convolutional Neural Networks
This work addresses the challenge of integrating human-like shape perception into cognitive AI systems, representing an incremental improvement by applying existing neural network methods to a new domain.
The paper tackled the problem of generalizing psychological shape similarity spaces to novel stimuli by learning a mapping from perceptual inputs to a psychological shape space using convolutional neural networks. The result showed that a classification-based multi-task learning approach performed best, but its performance was sensitive to the dimensionality of the similarity space.
Shape information is crucial for human perception and cognition, and should therefore also play a role in cognitive AI systems. We employ the interdisciplinary framework of conceptual spaces, which proposes a geometric representation of conceptual knowledge through low-dimensional interpretable similarity spaces. These similarity spaces are often based on psychological dissimilarity ratings for a small set of stimuli, which are then transformed into a spatial representation by a technique called multidimensional scaling. Unfortunately, this approach is incapable of generalizing to novel stimuli. In this paper, we use convolutional neural networks to learn a generalizable mapping between perceptual inputs (pixels of grayscale line drawings) and a recently proposed psychological similarity space for the shape domain. We investigate different network architectures (classification network vs. autoencoder) and different training regimes (transfer learning vs. multi-task learning). Our results indicate that a classification-based multi-task learning scenario yields the best results, but that its performance is relatively sensitive to the dimensionality of the similarity space.