Functional Equivalence with NARS
This research addresses the need for flexibility in learning and adaptation for achieving human-level artificial general intelligence (AGI), though it appears incremental as it modifies an existing system to incorporate functional equivalence.
This study tackled the problem of enabling functional equivalence in the Non-Axiomatic Reasoning System (NARS) via OpenNARS for Applications (ONA), allowing categorization based on utility rather than perceptual similarity, and demonstrated its utility in complex problem-solving and decision-making through practical examples, including training ONA to learn basic human-like language abilities.
This study explores the concept of functional equivalence within the framework of the Non-Axiomatic Reasoning System (NARS), specifically through OpenNARS for Applications (ONA). Functional equivalence allows organisms to categorize and respond to varied stimuli based on their utility rather than perceptual similarity, thus enhancing cognitive efficiency and adaptability. In this study, ONA was modified to allow the derivation of functional equivalence. This paper provides practical examples of the capability of ONA to apply learned knowledge across different functional situations, demonstrating its utility in complex problem-solving and decision-making. An extended example is included, where training of ONA aimed to learn basic human-like language abilities, using a systematic procedure in relating spoken words, objects and written words. The research carried out as part of this study extends the understanding of functional equivalence in AGI systems, and argues for its necessity for level of flexibility in learning and adapting necessary for human-level AGI.