Simulation of quantification abilities using a modular neural network approach

A novel modular neural network architecture and its application to the field of numerical cognition simulation are presented. Previous modular connectionist systems are typically constrained at one of two levels: at the representational level, in that the connectivity of the modules is hard-wired by the modeller; or at a local architectural level, in that the modeller explicitly allocates each module to a specific subtask. Our approach aims to minimise the constraints, thus reducing the bias possibly introduced by the modeller. The efficacy of this approach is demonstrated through the successful simulation of the development of two quantification abilities, subitising and counting, amongst children. It is concluded that such a minimally constrained modular system may contribute to both the capturing of learnt behaviour, and the allocation of modules to subtasks according to the nature of the task.