AUTHOR=Wang Pei , Hahm Christian , Hammer Patrick 

TITLE=A Model of Unified Perception and Cognition

JOURNAL=Frontiers in Artificial Intelligence

VOLUME=Volume 5 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2022.806403

DOI=10.3389/frai.2022.806403

ISSN=2624-8212

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