Computational Cognitive Modelling of Visual Attention

Abstract :

The emerging field of Computational Cognitive Neuroscience (CCN) lies at the intersection of computational neuroscience and the similar fields of machine learning, neural network theory, connectionism, psychology and artificial intelligence. The goal of computational cognitive neuroscience is to understand how the brain embodies the mind by using biologically based computational models. Modelling visual attention-particularly stimulus- driven, saliency-based attention has been a very active research area over the past 25 years. Many different models of attention are now available which, aside from lending theoretical contributions to other fields, have demonstrated successful applications in computer vision, mobile robotics, and cognitive systems. This work proposes a Computational Cognitive Neuroscience (CCN) model for visual attention in young adults. The aim of the proposed work is to develop a joint computational modelling of the structural-functional connectivity of the brain, along with cognitive and behavioural aspects during visual attention seeking process from eye tracking, EEG, fMRI and behavioural data. This model can provide insights into how visual attention process is implemented in a specific brain area, what leads to control and selection of where to attend in a scene, how the visual changes are perceived by brain as opposed to merely identifying where a particular process is located. Such modelling can be used to predict visual attention of both neuro-typical and to some extent neuro-atypical subjects. Even though variety of attention disorders such as attention deficit disorder, autism and schizophrenia, can now be reliably diagnosed, the origin of these disorders remain poorly understood. Developing targeted therapies for treating such disorders requires a mechanistic understanding of how attention works at the level of cells and circuits and we believe such computational models can help in the process. The application of such modelling are many, varying from driver assistance, device/software usability study, improving computer-human interactions, disease diagnosis, developing targeted therapies for treating disorders, mindfulness training, marketing and customer research etc.

Publication :