Abstract

A novel theory of reflective consciousness, will and self is presented, based on modeling each of these entities using self-referential mathematical structures called hypersets. Pattern theory is used to argue that these exotic mathematical structures may meaningfully be considered as parts of the minds of physical systems, even finite computational systems. The hyperset models presented are hypothesized to occur as patterns within the "moving bubble of attention" of the human brain and any roughly human-mind-like AI system. These ideas appear to be compatible with both panpsychist and materialist views of consciousness, and probably other views as well. Their relationship with the CogPrime AI design and its implementation in the OpenCog software framework is elucidated in detail.