clear query| facets| time Search criteria: author:"Ted Dunning".   Results from 21 to 30 from 5214 (0.0s).
Loading phrases to help you
refine your search...
Processing 50 millions of file for LDA - Mahout - [mail # user]
...Nishant,  It is hard to advise on detailed trade-offs for your case but I am pretty sure that there are other options than S3 which is, as you say, very slow in terms of latency due to ...
   Author: Ted Dunning , 2013-06-04, 09:12
[expand - 4 more] - Mahout beginner questions... - Mahout - [mail # user]
...On Sun, Mar 25, 2012 at 3:36 PM, Razon, Oren  wrote:  > ... > The system I need should of course give the recommendation itself in no > time. > ...  But because I'...
   Author: Ted Dunning , 2012-03-25, 22:55
[expand - 4 more] - Which maven command to use to put all the binaries into the distribution layout? - Mahout - [mail # user]
...Isn't there a mvn package target that is better for this?  On Fri, May 6, 2011 at 8:34 AM, Sean Owen  wrote:  > I think you'd have to set up release keys and all that to ma...
   Author: Ted Dunning , 2011-05-06, 16:07
[expand - 1 more] - Vectorizing arbitrary value types with seq2sparse - Mahout - [mail # user]
...This is definitely desirable but is very different from the current tool.  My guess is the big difficulty will be describing the vectorization to be done.  The hashed representatio...
   Author: Ted Dunning , 2011-05-06, 20:17
implicit data relative ratings - Mahout - [mail # user]
...Here is an interesting paper that claims that implicit rankings based on logging requests for directions are at least as good as explicit ratings and ten times more available.  http://w...
   Author: Ted Dunning , 2011-05-06, 22:50
[expand - 1 more] - Perfect neighbours - Mahout - [mail # user]
...That is a form of dimensionality reduction, but that is not what is normally meant by this.  Normally, dimensionality reduction is done by transforming the input space (dimension = numb...
   Author: Ted Dunning , 2009-06-01, 22:22
[expand - 1 more] - Relevance score - Classification - Mahout - [mail # user]
...You have both a training problem and a scalability problem here.  The training problem is that to build a classifier, you either need to make fairly gross assumptions about which featur...
   Author: Ted Dunning , 2011-11-24, 07:31
[expand - 3 more] - Hybrid RecSys — ways to do it - Mahout - [mail # user]
...When stacking recommenders, you need to have features that represent:  a) the output of the recommenders in question  b) features that you think will help.  Number of data poi...
   Author: Ted Dunning , 2011-06-10, 06:02
[expand - 1 more] - Tuning parameters for ALS-WR - Mahout - [mail # user]
...You definitely need to separate into three sets.  Another way to put it is that with cross validation, any learning algorithm needs to have test data withheld from it.  The remaini...
   Author: Ted Dunning , 2013-09-11, 05:16
Classifying general Attribute-Relation data using Mahout - Mahout - [mail # user]
...Martin,  I saw only one attachment here.  The other may have been stripped by the mailing list which prefers not to have attachments.  I have filed an issue for this at https:...
   Author: Ted Dunning , 2010-02-09, 18:40