Null Dynamical State Models of Human Cognitive Dysfunction
This work addresses the fundamental philosophical problem of qualia in AI by linking machine learning dynamics to human cognitive phenomena, though it appears incremental in applying existing dynamical concepts to this domain.
The paper tackles the hard problem of artificial intelligence by modeling human cognitive dysfunction as a natural response of learning machines to novel inputs outside their training distribution, showing that such machines enter null dynamical states that predict and explain human semantic experiences like confusion and grief.
The hard problem in artificial intelligence asks how the shuffling of syntactical symbols in a program can lead to systems which experience semantics and qualia. We address this question in three stages. First, we introduce a new class of human semantic symbols which appears when unexpected and drastic environmental change causes humans to become surprised, confused, uncertain, and in extreme cases, unresponsive, passive and dysfunctional. For this class of symbols, pre-learned programs become inoperative so these syntactical programs cannot be the source of experienced qualia. Second, we model the dysfunctional human response to a radically changed environment as being the natural response of any learning machine facing novel inputs from well outside its previous training set. In this situation, learning machines are unable to extract information from their input and will typically enter a dynamical state characterized by null outputs and a lack of response. This state immediately predicts and explains the characteristics of the semantic experiences of humans in similar circumstances. In the third stage, we consider learning machines trained to implement multiple functions in simple sequential programs using environmental data to specify subroutine names, control flow instructions, memory calls, and so on. Drastic change in any of these environmental inputs can again lead to inoperative programs. By examining changes specific to people or locations we can model human cognitive symbols featuring these dependencies, such as attachment and grief. Our approach links known dynamical machines states with human qualia and thus offers new insight into the hard problem of artificial intelligence.