The following is my summary of the article entitled
"A Cognitive Substrate for Achieving Human-Level Intelligence" (AI Magazine 2006).
The profusion problem:
For intelligent systems to be broadly functional and robust, the profusion of knowledge, data structures and algorithms must be integrated.
The Cognitive Substrate
Hypothesis
There is certain cognitive substrates to solve a relatively small set of computational problems with which other cognitive tasks can be solved.
"These include reasoning about temporal intervals, causal relations, identities between objects and events, ontologies, beliefs, and desires."
Findings in linguistic semantics (e.g., Jackendoff) support the hypothesis.Polyscheme cognitive architecture (Cassimatis 2005)
The common function principle (CFP): Many AI algorithms can be implemented in terms of the same basic set of common functions.
The multiple implementation principle (MIP): Each common function can be implemented using multiple computational methods.
The article tries to show a parallel between (folk) physical concepts and grammatical concepts.
I agree with the problem setting (the profusion problem) and am also hopeful with the cognitive substrate hypothesis. I am less sure about Polyscheme, as it is a more practical architecture issue, though the two principles would be desired.
For anyone pursuing a brain-inspired cognitive architecture, the integration issue would be a keener problem, as they often start from learning issues and leave other problems (of planning, language processing, etc.) aside... (This is not a comment on the article above, but a more general comment.)
Dr. Cassimatis is on the faculty of the Cognitive Science Department at Rensselaer, and has founded a search technology company SkyPhase.
I agree with the problem setting (the profusion problem) and am also hopeful with the cognitive substrate hypothesis. I am less sure about Polyscheme, as it is a more practical architecture issue, though the two principles would be desired.
For anyone pursuing a brain-inspired cognitive architecture, the integration issue would be a keener problem, as they often start from learning issues and leave other problems (of planning, language processing, etc.) aside... (This is not a comment on the article above, but a more general comment.)
Dr. Cassimatis is on the faculty of the Cognitive Science Department at Rensselaer, and has founded a search technology company SkyPhase.
No comments:
Post a Comment