Functional Equivalence with NARS

TL;DR

This paper investigates how the OpenNARS system can be modified to incorporate functional equivalence, enabling more flexible and adaptive reasoning akin to human cognition, with practical applications in language learning and problem-solving.

Contribution

It introduces modifications to OpenNARS to derive functional equivalence, demonstrating improved adaptability and practical reasoning capabilities in AGI systems.

Findings

ONA can apply learned knowledge across different functional situations

Training enables basic human-like language abilities in ONA

Functional equivalence enhances cognitive flexibility in AGI

Abstract

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.