This article is moderately interesting...
Basically, though, it just represents a couple excellent but very
traditional cog-sci researchers describing their view of what general
intelligence is, and why existing AI approaches don't come anywhere near
it...
The authors are creators of the ACT-R architecture, which is perhaps the
best of the mainstream AI approaches out there(though I don't personally
think it has a prayer of becoming an AGI ;)
They don't really distinguish between AGI and human-cognition-simulation,
unfortunately....
-- Ben
**************
The Newell Test for a Theory of Mind
by
John R. Anderson and Christian Lebiere
Carnegie Mellon University
http://www.bbsonline.org/Preprints/Anderson/Referees/
The Newell Test for a Theory of Mind
John R. Anderson
Department of Psychology – BH345D
Carnegie Mellon University
Christian Lebiere
Human Computer Interaction Institute
Carnegie Mellon University
ABSTRACT: Newell (1980, 1990) proposed that cognitive theories be developed
trying to satisfy multiple criteria to avoid theoretical myopia. He
provided two overlapping lists of 13 criteria that the human cognitive
architecture would have to satisfy to be functional. We have distilled
these into 12: flexible behavior, real-time performance, adaptive behavior,
vast knowledge base, dynamic behavior, knowledge integration, natural
language, learning, development, evolution, and brain realization. There
would be greater theoretical progress if we evaluated theories by a broad
set of criteria such as these and attended to the weaknesses such
evaluations revealed. To illustrate how theories can be evaluated we apply
them to both classical connectionism (McClelland & Rumelhart, 1986;
Rumelhart & McClelland, 1986) and the ACT-R theory (Anderson & Lebiere,
1998). The strengths of classical connectionism on this test derive from
its intense effort in addressing empirical phenomena in domains like
language and cognitive development. Its weaknesses derive from its failure
to acknowledge a symbolic level to thought. In contrast, ACT-R includes
both symbolic and subsymbolic components. The strengths of the ACT-R derive
from its tight integration of the symbolic with the subsymbolic. Its
weaknesses largely derive from its failure as yet to adequately engage in
intensive analyses of issues related to certain criteria on Newell’s list
KEYWORDS: Cognitive Architecture; Connectionism; Hybrid Systems; Language
Learning; Symbolic Systems
-------
To unsubscribe, change your address, or temporarily deactivate your subscription,
please go to http://v2.listbox.com/member/
