Mesarovician Abstract Learning Systems
This work addresses a foundational theoretical gap in AGI research by shifting focus from problem-solving to the systems themselves, though it appears incremental as it builds on existing general systems theory.
The paper tackles the inadequacy of current domain-task frameworks for modeling artificial general intelligence (AGI) by proposing a meta-theory based on Mesarovician abstract systems theory, which formulates abstract learning systems and stratifies assumptions into a hierarchy to refocus on learning systems rather than problems.
The solution methods used to realize artificial general intelligence (AGI) may not contain the formalism needed to adequately model and characterize AGI. In particular, current approaches to learning hold notions of problem domain and problem task as fundamental precepts, but it is hardly apparent that an AGI encountered in the wild will be discernable into a set of domain-task pairings. Nor is it apparent that the outcomes of AGI in a system can be well expressed in terms of domain and task, or as consequences thereof. Thus, there is both a practical and theoretical use for meta-theories of learning which do not express themselves explicitly in terms of solution methods. General systems theory offers such a meta-theory. Herein, Mesarovician abstract systems theory is used as a super-structure for learning. Abstract learning systems are formulated. Subsequent elaboration stratifies the assumptions of learning systems into a hierarchy and considers the hierarchy such stratification projects onto learning theory. The presented Mesarovician abstract learning systems theory calls back to the founding motivations of artificial intelligence research by focusing on the thinking participants directly, in this case, learning systems, in contrast to the contemporary focus on the problems thinking participants solve.