How communication can improve differentiation in the Modeling Field Theory framework

We propose a discrimination task scenario to study language acquisition in which an agent receives linguistic input from an external teacher, in addition to the sensory stimuli from the objects that make up the environment. The agent is endowed with the modeling field theory (MFT) categorization mechanism, which enables it to identify a few objects (or categories) composed of hundreds of random pixels (instances). We show that the agent with language is capable of differentiating objects or categories that it could not distinguish without language