VICE: Variational Interpretable Concept Embeddings
A central goal in the cognitive sciences is the development of numerical models for mental representations of object concepts. This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for embedding object concepts in a vector space using data collected from humans in an odd-one-out triplet task. VICE uses variational inference to obtain sparse, non-negative representations of object concepts with uncertainty estimates for the embedding values. These estimates are used to automatically select the dimensions that best explain the data. We derive a PAC learning bound for VICE that can be used to estimate generalization performance or determine sufficient sample size in experimental design. VICE rivals or outperforms its predecessor, SPoSE, at predicting human behavior in the odd-one-out triplet task. Furthermore, VICE's object representations are more reproducible and consistent across random initializations.
READ FULL TEXT