A Model for Artificial General Intelligence
Loading...
Date
2020-04-17
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
A Functional Modeling Framework (FMF) for defining and comparing models of consciousness and cognition has recently been developed. This framework proposes to have the capacity to represent the complete set of the functionality of human consciousness and cognition, which if true, would suggest that all models of consciousness and cognition can be represented within the framework. The framework also proposes to define the criteria for a model of cognition to have the potential for the general problem solving ability commonly recognized as true human intelligence. The FMF provides a single framework for defining models of consciousness and cognition that is human-centric in that the functions can be validated through experiments that can be performed within innate human self-awareness rather than being dependent on assumptions made by any specific model. This human-centric functional modeling approach is intended to enable different models of AGI to be more easily compared so research can reliably converge on a single understanding, enabling the possibility of massively collaborative interdisciplinary projects to research, and implement models of consciousness or cognition where such massive collaboration has not proved possible before. The FMF defines requirements for all the functional components defined by the framework, but leaves specific models to define their own implementations. This paper summarizes a model of cognition developed within this framework that is proposed to meet the criteria of an AGI as defined within this framework. This description is expanded in a number of other papers.
Description
Keywords
AGI, Artificial General Intelligence, Functional Modeling