| clear query|facets|time |
Search criteria: .
Results from 111 to 120 from
697 (1.009s).
|
|
|
Loading phrases to help you
refine your search...
|
|
Re: alternating least squares - Mahout - [mail # user]
|
|
...Hi Koobas, We have two classes that implement the solutions described in the ALS-related papers: For explicit feedback data [1] we have AlternatingLeastSquaresSolver, for implici...
|
|
|
Author: Sebastian Schelter,
2013-01-08, 21:03
|
|
|
Re: Parameter choice and tuning parallelALS - Mahout - [mail # user]
|
|
...Hi Pat, ParallelALSFactorizationJob actually implements two different flavours of matrix factorization, one that is aimed at explicit feedback data (such as ratings): "Large-scal...
|
|
|
Author: Sebastian Schelter,
2013-01-02, 16:46
|
|
|
Re: LSA in Mahout - Mahout - [mail # user]
|
|
...Hi Osman, Mahout has all the building blocks you need to create a LSA pipeline: You have to vectorize your documents using seqdirectory and seq2sparse to get the term-document-ma...
|
|
|
Author: Sebastian Schelter,
2012-12-26, 19:59
|
|
|
Re: Matrix Factorization with Implicit Feedback - Mahout - [mail # user]
|
|
...The usage seems to be ok, I'm not sure whether the learning rate value (lambda) works well for the implicit variant of the algorithm, though. The algorithm should work with binary data...
|
|
|
Author: Sebastian Schelter,
2012-12-10, 16:41
|
|
|
Re: Matrix Factorization with Implicit Feedback - Mahout - [mail # user]
|
|
...Hi Royi, If you specify implicitFeedback=true, then another variant of ALS is used that is described in this paper: Collaborative Filtering for Implicit Feedback Datasets www2.re...
|
|
|
Author: Sebastian Schelter,
2012-12-10, 16:18
|
|
|
[MAHOUT-1124] Deprecate ununsed recommenders - Mahout - [issue]
|
|
...Deprecating some recommenders for the following reasons:org.apache.mahout.cf.taste.impl.recommender.svd.FunkSVDFactorizerRatingSGDFactorizer should be learning faster and has a nicer model a...
|
|
|
http://issues.apache.org/jira/browse/MAHOUT-1124
Author: Sebastian Schelter,
2012-12-07, 10:13
|
|
|
[MAHOUT-924] Allow creation of symmetric adjacency matrices - Mahout - [issue]
|
|
...org.apache.mahout.graph.AdjacencyMatrixJob should allow the creation of symmetric adjacency matrices (which correspond to an undirected graph)...
|
|
|
http://issues.apache.org/jira/browse/MAHOUT-924
Author: Sebastian Schelter,
2012-12-07, 08:54
|
|
|
Re: Remove unused recommenders? - Mahout - [mail # user]
|
|
...I concur that deprecation is a better way than simply removing the classes. Will do so, thanks. /s On 07.12.2012 03:38, Marty Kube wrote:...
|
|
|
Author: Sebastian Schelter,
2012-12-07, 08:52
|
|
|
Re: Remove unused recommenders? - Mahout - [mail # user]
|
|
...FunkSVD is a suboptimal duplicate of RatingSGDFactorizer, ImplicitLinearRegressionFactorizer is a duplicate of ALSWR so I think we should only keep one of each. The other three recomme...
|
|
|
Author: Sebastian Schelter,
2012-12-06, 15:21
|
|
|
Remove unused recommenders? - Mahout - [mail # user]
|
|
...Hi there, I'm currently thinking whether we should do a little cleanup in the non-distributed recommenders package and throw out recommenders that have not been used/asked about on the...
|
|
|
Author: Sebastian Schelter,
2012-12-06, 15:06
|
|
|
|
