Concept based Attention
It addresses a fundamental problem in understanding cognitive processes for AI and neuroscience, but appears incremental as it builds on existing attention theories.
The paper proposes concept based attention (CbA) as a mechanism for high-level cognition, suggesting that attention in humans and advanced animals is driven by abstract perceptions rather than simple features.
Attention endows animals an ability to concentrate on the most relevant information among a deluge of distractors at any given time, either through volitionally 'top-down' biasing, or driven by automatically 'bottom-up' saliency of stimuli, in favour of advantageous competition in neural modulations for information processing. Nevertheless, instead of being limited to perceive simple features, human and other advanced animals adaptively learn the world into categories and abstract concepts from experiences, imparting the world meanings. This thesis suggests that the high-level cognitive ability of human is more likely driven by attention basing on abstract perceptions, which is defined as concept based attention (CbA).