A Model of Unified Perception and Cognition

Abstract

This article discusses an approach to add perception functionality to a general-purpose intelligent system, NARS. Differently from other AI approaches toward perception, our design is based on the following major opinions: (1) Perception primarily depends on the perceiver, and subjective experience is only partially and gradually transformed into objective (intersubjective) descriptions of the environment; (2) Perception is basically a process initiated by the perceiver itself to achieve its goals, and passive receiving of signals only plays a supplementary role; (3) Perception is fundamentally unified with cognition, and the difference between them is mostly quantitative, not qualitative. The directly relevant aspects of NARS are described to show the implications of these opinions in system design, and they are compared with the other approaches. Based on the research results of cognitive science, it is argued that the Narsian approach better fits the need of perception in Artificial General Intelligence (AGI).

Keywords: AGI; NARS; learning; reasoning; unified model.

Figure 1

In this screenshot, NARS executes an operation indicating it recognizes an image of digit zero. The videos documenting the trials in the table are available on YouTube (Binary Memorization; Digit Memorization; Binary Classification; Digit Classification).