Revealing interpretable object representations from human behavior
This work addresses how mental object representations relate to human behavior, with potential applications in psychology and AI, but it is incremental as it builds on existing methods for representation estimation.
The researchers tackled the problem of understanding mental object representations by estimating sparse, non-negative representations from human behavioral judgments on 1,854 object categories, which predicted a latent similarity structure capturing most of the explainable variance in human judgments and were interpretable as conveying taxonomic, functional, and perceptual attributes.
To study how mental object representations are related to behavior, we estimated sparse, non-negative representations of objects using human behavioral judgments on images representative of 1,854 object categories. These representations predicted a latent similarity structure between objects, which captured most of the explainable variance in human behavioral judgments. Individual dimensions in the low-dimensional embedding were found to be highly reproducible and interpretable as conveying degrees of taxonomic membership, functionality, and perceptual attributes. We further demonstrated the predictive power of the embeddings for explaining other forms of human behavior, including categorization, typicality judgments, and feature ratings, suggesting that the dimensions reflect human conceptual representations of objects beyond the specific task.