Open AccessA Cognitive Substrate for Achieving Human‐Level Intelligence
Author(s) -
Cassimatis Nicholas L.
Publication year - 2006
Publication title -
ai magazine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.597
H-Index - 79
eISSN - 2371-9621
pISSN - 0738-4602
DOI - 10.1609/aimag.v27i2.1879
Subject(s) - computer science , human intelligence , embodied cognition , cognition , cognitive architecture , cognitive science , artificial general intelligence , set (abstract data type) , cognitive robotics , artificial intelligence , neural substrate , parsing , human–computer interaction , natural language processing , psychology , programming language , neuroscience
Making progress toward human‐level artificial intelligence often seems to require a large number of difficult‐to‐integrate computational methods and enormous amounts of knowledge about the world. This article provides evidence from linguistics, cognitive psychology, and neuroscience for the cognitive substrate hypothesis that a relatively small set of properly integrated data structures and algorithms can underlie the whole range of cognition required for human‐level intelligence. Some computational principles (embodied in the Polyscheme cognitive architecture) are proposed to solve the integration problems involved in implementing such a substrate. A natural language syntactic parser that uses only the mechanisms of an infant physical reasoning model developed in Polyscheme demonstrates that a single cognitive substrate can underlie intelligent systems in superficially very dissimilar domains. This work suggests that identifying and implementing a cognitive substrate will accelerate progress toward human‐level artificial intelligence.