Skip to content

HTTPS clone URL

Subversion checkout URL

You can clone with HTTPS or Subversion.

Download ZIP
Fetching contributors…

Cannot retrieve contributors at this time

80 lines (40 sloc) 4.713 kb
How to contribute to #mymedialite: http://ismll.de/mymedialite/contribute.html #recsys #opensource #freesoftware #mono #csharp
If you are interested in recommender systems and personalization, have a look at http://recsyswiki.com #recsys
Implementing new recommenders for #mymedialite: bit.ly/mTX6U3 It is very easy! #recsys #csharp
Using the #mymedialite recommender system library from #Ruby: http://ismll.de/mymedialite/do… #ironruby #recsys
Using the #mymedialite recommender system library from #Python: http://bit.ly/qYBG3L #recsys #ironpython #personalization
Using the #mymedialite recommender system library in C# programs: http://bit.ly/nkPfF0 #csharp #dotnet #cli #recsys #mono
#mymedialite recommender system library: FAQ and documentation overview: http://ismll.de/mymedialite/documentation/index.html #recsys
Using the #mymedialite item prediction command-line tool: http://ismll.de/mymedialite/documentation/item_prediction.html #recsys
The #mymedialite rating prediction tool lets you to train+evaluate rating prediction models: http://bit.ly/nsKUGZ #recsys
Learn how to use the #mymedialite command line tools: http://ismll.de/mymedialite/documentation/command_line.html #recsys
The #mymedialite API documentation can be found here: http://ismll.de/mymedialite/documentation/doxygen/ #recsys
Questions about using #mymedialite? Ask them in our Google group: https://groups.google.com/group/mymedialite #recsys
Follow and/or fork MyMediaLite on github: https://github.com/zenogantner/MyMediaLite #mymedialite #recsys
#MyMediaLite at #mlcomp: mlcomp.org/datasets/335 mlcomp.org/datasets/351 #recsys
You can reach the authors of #MyMediaLite by sending an e-mail to mymedialite@ismll.de.
Subscribe to #MyMediaLite updates on freshmeat.net & mloss.org http://freshmeat.net/projects/mymedialite http://mloss.org/software/view/282/
If you want to cite #MyMediaLite in your paper, use this #BibTeX entry: http://mloss.org/revision/paperbib/811/ #recsys
WR-MF is a state-of-the-art matrix factorization model for item recommendation: http://bit.ly/o6v2QP #MyMediaLite #recsys
BPR-MF is a state-of-the-art matrix factorization model for item recommendation: http://bit.ly/pYrJ7l #MyMediaLite #recsys
#MyMediaLite supports the tasks of rating prediction and item recommendation: http://bit.ly/qhMI5V http://bit.ly/qlNDbY #recsys
Since version 1.05, #MyMediaLite supports recommendations for groups: http://ismll.de/mymedialite/news/index.html#1.05 #recsys
#MyMediaLite supports different evaluation protocols, e.g. simple splits and k-fold cross-validation: http://bit.ly/nbykPh #recsys
We also have a nice GUI demo: http://bit.ly/pvXuSB #MyMediaLite #recsys
#MyMediaLite scales pretty well: For small models, 1 iteration over the Netflix dataset takes < 100 seconds: http://bit.ly/pQxTYZ #recsys
BiasedMatrixFactorization is a state-of-the-art matrix factorization model for rating prediction: http://bit.ly/ooNlpb #recsys #MyMediaLite
#MyMediaLite contains different kNN models for both rating and item prediction: http://bit.ly/pscX4U http://bit.ly/no1sam #recsys
BPR_Linear in #MyMediaLite is an attribute-based model for personalized item ranking: http://bit.ly/mV5lal #recsys
Rate #MyMediaLite on ohloh.net: https://www.ohloh.net/p/mymedialite #recsys
You can download #MyMediaLite here: http://ismll.de/mymedialite/download/index.html #recsys
Read the #recsys2011 paper on #MyMediaLite: http://ismll.de/pub/pdfs/Gantner_et_al2011_MyMediaLite.pdf #recsys
Read about our approach for #kddcup2011: http://ismll.de/pub/pdfs/Gantner_et_al2011_KDDCup.pdf #recsys #MyMediaLite
Overview of open source/free software recommender system implementations: http://www.ismll.uni-hildesheim.de/mymedialite/links.html
Research that builds on the #MyMediaLite library: http://ismll.de/mymedialite/examples/research.html #recsys
predictive accuracy of different #MyMediaLite recommenders on rating prediction datasets: http://bit.ly/p6Bzbj #recsys
The #MyMediaLite issue/bug tracker: https://github.com/zenogantner/MyMediaLite/issues #recsys
#MyMediaLite feature overview: http://ismll.de/mymedialite/features.html #recsys
#MyMediaLite item recommendation tool: --rating-threshold=4 interprets all ratings > 4 as positive feedback
If you are a Java developer, this may help you to learn about C#: http://www.25hoursaday.com/CsharpVsJava.html
How to call #MyMediaLite from F#: https://github.com/zenogantner/MyMediaLite/blob/master/examples/fsharp/item_recommendation.fs https://github.com/zenogantner/MyMediaLite/blob/master/examples/fsharp/rating_prediction.fs #recsys
#MyMediaLite has a Java port: https://github.com/jcnewell/MyMediaLiteJava initiated by @JCWNewell #recsys
Jump to Line
Something went wrong with that request. Please try again.