On Thu, Apr 4, 2013 at 6:43 PM, Telmo Menezes <te...@telmomenezes.com>wrote:

> There probably isn't a general learning algorithm there are just lots of
>> lesser learning algorithms,
>>
>
> > Then you need a higher-level algorithm to decide which lesser algorithm
> to use for each situation.
>

Yes, or use a rule of thumb to decide on a algorithm, or use lots of
algorithms and check for one that gives a reasonable sounding answer.

> and more important than any algorithm or even deduction in general are
>> rules of thumb, like induction.
>>
>
> I don't understand the distinction. Rules of thumb and induction seem
> algorithmic to me.


Within their domain of applicability algorithms can be proven to ALWAYS
work; rules of thumb USUALLY work and even that can not be proven but is
know through induction and sometimes, not usually but sometimes, induction
can be wrong. So just like us even a computerized Jupiter brain would not
be immune from error.

  John K Clark

-- 
You received this message because you are subscribed to the Google Groups 
"Everything List" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to everything-list+unsubscr...@googlegroups.com.
To post to this group, send email to everything-list@googlegroups.com.
Visit this group at http://groups.google.com/group/everything-list?hl=en.
For more options, visit https://groups.google.com/groups/opt_out.


Reply via email to