Fluid Intelligence and Time Management and Artificial Neural Networks

Abstract

Attention deficit hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by inattention, hyperactivity, and impulsivity. Our lab is currently conducting a pilot study to assess the effects of the online game Minecraft as a therapeutic video game (TVG) to train executive function deficits in children with ADHD. The effect of the TVG intervention in combination with stimulants is being investigated to develop a drug-device combination therapy that can address both the dopaminergic dysfunction and executive function deficits present in ADHD. Although the results of this study will be used to guide the clinical development process, additional guidance for the optimization of the executive function training activities will be provided by a computational model of executive functions built with artificial neural networks (ANNs). This model uses ANNs to complete virtual tasks resembling the executive function training activities that the study subjects practice in the Minecraft world, and the schedule of virtual tasks that result in maximum improvements in ANN performance on these tasks will be investigated as a method to inform the selection of training regimens in future clinical studies. This study first proposes the use of recurrent neural networks to model the fluid intelligence executive function. This model is then combined with a previously developed model using convolutional neural networks to model working memory and prepotent impulsivity to produce virtual "subjects" who complete a computational simulation of a Time Management task that requires the use of both of these executive functions to complete. The capability of this model to produce groups of virtual subjects with significantly different levels of performance on the Time Management task is demonstrated.