An analogical inductive solution to the grounding problem

The Causal Cognitive Architecture 5, a brain inspired cognitive architecture, is presented. The navigation map which holds features, procedures, and linkages in its spatially mapped cells, is the basic data structure of the architecture. By enhancing the feedback processing of intermediate results n...

Full description

Saved in:
Bibliographic Details
Published in:Cognitive systems research 2023-01, Vol.77, p.174-216
Main Author: Schneider, Howard
Format: Article
Language:English
Subjects:
Analogies
Artificial general intelligence (AGI)
Brain-inspired cognitive architecture (BICA)
Causality
Cognitive architecture
Embodied cognition
Grounding problem
Hippocampus
Navigation maps
World models
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The Causal Cognitive Architecture 5, a brain inspired cognitive architecture, is presented. The navigation map which holds features, procedures, and linkages in its spatially mapped cells, is the basic data structure of the architecture. By enhancing the feedback processing of intermediate results not only can causal abilities emerge but as well inductive analogical processing readily emerges as a core mechanism of the architecture. It is shown that abstract or poor features or concepts which cannot readily be grounded in sensorimotor interactions with the environment, can effectively be grounded via the core inductive analogical processing of the architecture, and provides a performance advantage in solving problems. As well, it is shown that relatively small changes in architecture can allow analogical reasoning and a solution to the grounding problem to emerge in a brain-inspired navigation map-based architecture.
ISSN:1389-0417
1389-0417
DOI:10.1016/j.cogsys.2022.10.005