In one word: learning. 
>
> In one sentence: Mine the history of inferences and ask the system to 
> come up with inference control patterns that may speed up future 
> inferences. 


So you are saying that you should use learning algorithms to pick out 
potentially useful inference chains.  I feel like our brains probably 
approach it in a similar way so I guess I can agree that is a good starting 
point.  But I am wondering if it may be limiting the set of problems that 
can be solved to those that we humans can already solve.  To solve the hard 
problems -- cancer, aging, Rubiks cube -- maybe we need wildly 
unconventional thinking sequences.   For something as important as 
inference maybe it would be warranted to find a few shortcuts instead of 
relying totally on learning -- at least in the beginning if not always.

-- 
You received this message because you are subscribed to the Google Groups 
"opencog" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
To post to this group, send email to [email protected].
Visit this group at https://groups.google.com/group/opencog.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/opencog/6e654517-e88d-49e8-9551-d1bce4ff2384%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.

Reply via email to