Modelling the development of counting with memory-augmented neural networks

Abstract

Learning to count is an important example of the broader human capacity for systematic generalization, and the development of counting is often characterized by an inflection point when children rapidly acquire proficiency with the procedures that support this ability. We aimed to model this process by training a reinforcement learning agent to select N items from a binary vector when instructed (known as the give-N task). We found that a memory-augmented modular network architecture based on the recently proposed Emergent Symbol Binding Network (ESBN) exhibited an inflection during learning that resembled human development. This model was also capable of systematic extrapolation outside the range of its training set -for example, trained only to select between 1 and 10 items, it could succeed at selecting 11 to 15 items as long as it could make use of an arbitrary count sequence of at least that length. The close parallels to child development and the capacity for extrapolation suggest that our model could shed light on the emergence of systematicity in humans.

When working memory may be just working, not memory.

“…Indeed, a growing number of models suggest interactions between EM and WM may be a central, not just an incidental feature of cognitive function (A. Baddeley, 2000; Beukers et al, 2021; Cowan, 1999, 2019; Dulberg et al, 2021; Foster et al, 2019; Oberauer, 2009; Rose, 2020; Webb et al, 2021). For example, Cohen and O’Reilly (1996) proposed that an interaction between these systems may provide an account of prospective memory—that is, remembering to perform a task in the future (Einstein & McDaniel, 2005)—in which EM serves to store an association between a representation of the desired task and the circumstances in which it is to be performed, so that the task representation can be retrieved when those circumstances occur.…”