Taxonomic and Whole Object Constraints: A Deep Architecture

AbstractWe propose a neural network model that accounts for the emergence of the taxonomic constraint and for the whole object constraint in early word learning. Our proposal is based on Mayor and Plunkett (2010)’s neurocomputational model of the taxonomic constraint and extends it in two directions. Firstly, we deal with realistic visual and acoustic stimuli. Secondly, we model the well-known whole object constraint in the visual component. We show that, despite the augmented input complexity, the proposed model compares favorably with respect to previous systems.


Return to previous page