On Tue, 8 Oct 2002, Tim Sweetman wrote:
Well, sort of - search engines find documents to fit certain criteria;
this tries to find documents similar to other documents.
Aeguably part of the same problem space though. I don't know where you can
find them anymore [ironically], but when it was
On Wed, Oct 09, 2002 at 07:48:32AM -0400, Chris Devers wrote:
On Tue, 8 Oct 2002, Tim Sweetman wrote:
Well, sort of - search engines find documents to fit certain criteria;
this tries to find documents similar to other documents.
Aeguably part of the same problem space though. I don't
At 10:05 09/10/02, Andy Wardley wrote:
I even wrote some Perl code to test it out... but I can't find that
either.
I'm *sure* I read it... I *wasn't* just dreaming...
I think there may be something wrong when you start dreaming algorythms and
perl..
:-)
Alex
Openweb Analysts Ltd,
Chris Devers wrote:
On Tue, 8 Oct 2002, Tim Sweetman wrote:
Well, sort of - search engines find documents to fit certain criteria;
this tries to find documents similar to other documents.
Arguably part of the same problem space though. I don't know where you can
find them anymore
On Wed, Oct 09, 2002 at 05:26:31PM +0100, Alex McLintock wrote:
At 10:05 09/10/02, Andy Wardley wrote:
I even wrote some Perl code to test it out... but I can't find that
either.
I'm *sure* I read it... I *wasn't* just dreaming...
I think there may be something wrong when you start
On Tue, Oct 08, 2002 at 11:23:59AM +0100, nemesis wrote:
Hello again,
I have a database (mySQL) full of variable length text fields (average
about 1500 characters, 250 words). Curently there are about 250 fields,
but I hope this to expand to as many as possible (it is an online joke
alex wrote:
probably completely crap but following is an approach i have been thinking
about for a while and have been looking for the right soft/textual dataset
to try it out on.
Thanks everyone for the suggestions. I certainly have some more ideass to work on.
Will
On Tue, 8 Oct 2002, alex wrote:
so, in your particular example you could try a 26 dimensional space where
each dimension is the frequency of a particular letter in the alphabet. if
This will fail for the same reason that this is a crappy hash algorithm.
All English sentences tend to have the
On Tue, 8 Oct 2002, alex wrote:
indeed - i seem to vaguely remember that i didn't use the sqrt in my
postal sector[0] comparisons (it was to calculate nearest specsavers
retail outlets to a postcode) and sql looked something like this:
Metric space theory tells you that your distance
On Tue, Oct 08, 2002 at 12:11:38PM +0100, Shevek wrote:
On Tue, 8 Oct 2002, alex wrote:
indeed - i seem to vaguely remember that i didn't use the sqrt in my
postal sector[0] comparisons (it was to calculate nearest specsavers
retail outlets to a postcode) and sql looked something like
On Tue, 8 Oct 2002, Ben wrote:
On Tue, Oct 08, 2002 at 12:11:38PM +0100, Shevek wrote:
Metric space theory tells you that your distance computation is valid
whether you square or not. It's still a valid metric. The unit ball is a
slightly different shape ...
Nonsense.
d(x,y) = (x1
On Tue, Oct 08, 2002 at 11:43:47AM +0100, alex wrote:
sqrt( (x0-x1)^2 + (y0-y1)^2 + (z0-z1)^2)
so, in your particular example you could try a 26 dimensional space where
each dimension is the frequency of a particular letter in the alphabet. if
I think you will find that this
12 matches
Mail list logo
