Databases
StackOverflow2013
Postsdbo
PO
 

Note that there are some explanatory texts on larger screens.

plurals
  1. PO
    primarykey
    data
    text
    <p>The problem you are trying to solve is called "collaborative filtering". </p> <h3>Neural Networks</h3> <p>One state-of-the-art neural network method is <em>Deep Belief Networks</em> and <em>Restricted Boltzman Machines</em>. For a fast python implementation for a GPU (CUDA) see <a href="http://peekaboo-vision.blogspot.com/2010/11/restricted-boltzmann-machine-on-cuda.html" rel="nofollow noreferrer">here</a>. Another option is <a href="http://pybrain.org/pages/features" rel="nofollow noreferrer">PyBrain</a>.</p> <p>Academic papers on your specific problem:</p> <ul> <li><p>This is probably the state-of-the-art of neural networks and collaborative filtering (of movies): </p> <blockquote> <p>Salakhutdinov, R., Mnih, A. Hinton, G, Restricted Boltzman Machines for Collaborative Filtering, To appear in Proceedings of the 24th International Conference on Machine Learning 2007. <a href="http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.94.5922&amp;rep=rep1&amp;type=pdf" rel="nofollow noreferrer">PDF</a></p> </blockquote></li> <li><p>A Hopfield network implemented in Python:</p> <blockquote> <p>Huang, Z. and Chen, H. and Zeng, D. Applying associative retrieval techniques to alleviate the sparsity problem in collaborative filtering. ACM Transactions on Information Systems (TOIS), 22, 1,116--142, 2004, ACM. <a href="http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.3.1590&amp;rep=rep1&amp;type=pdf" rel="nofollow noreferrer">PDF</a></p> </blockquote></li> <li><p>A thesis on collaborative filtering with Restricted Boltzman Machines (they say Python is not practical for the job):</p> <blockquote> <p>G. Louppe. Collaborative filtering: Scalable approaches using restricted Boltzmann machines. Master's thesis, Universite de Liege, 2010.<br> <a href="http://orbi.ulg.ac.be/bitstream/2268/74400/3/glouppe10-msc-thesis.pdf" rel="nofollow noreferrer">PDF</a></p> </blockquote></li> </ul> <p>Neural networks are not currently the state-of-the-art in collaborative filtering. And they are not the simplest, wide-spread solutions. Regarding your comment about the reason for using NNs being having too little data, neural networks don't have an inherent advantage/disadvantage in that case. Therefore, you might want to consider simpler Machine Learning approaches. </p> <h3>Other Machine Learning Techniques</h3> <p>The best methods today mix <em>k-Nearest Neighbors</em> and <em>Matrix Factorization</em>. </p> <p>If you are locked on Python, take a look at <a href="http://code.google.com/p/pysuggest/" rel="nofollow noreferrer">pysuggest</a> (a Python wrapper for the SUGGEST recommendation engine) and <a href="http://code.google.com/p/pyrsvd/" rel="nofollow noreferrer">PyRSVD</a> (primarily aimed at applications in collaborative filtering, in particular the Netflix competition). </p> <p>If you are open to try other open source technologies look at: <a href="https://stackoverflow.com/questions/659599/open-source-collaborative-filtering-frameworks">Open Source collaborative filtering frameworks</a> and <a href="http://www.infoanarchy.org/en/Collaborative_Filtering" rel="nofollow noreferrer">http://www.infoanarchy.org/en/Collaborative_Filtering</a>.</p>
    singulars
    1. This table or related slice is empty.
    1. PONeural Network based ranking of documents
      singulars
      1. PTQuestion
    1. PTAnswer
    1. This table or related slice is empty.
    1. UScyborg
    plurals
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. PONeural Network based ranking of documents
      singulars
      1. PTQuestion
    1. This table or related slice is empty.
    1. VO
      singulars
      1. PO
      1. This table or related slice is empty.
      1. VTAcceptedByOriginator
    2. VO
      singulars
      1. PO
      1. This table or related slice is empty.
      1. VTUpMod
    3. VO
      singulars
      1. PO
      1. This table or related slice is empty.
      1. VTUpMod
    1. COIs it a bad idea to use neural network along with collaborative filtering?.
      singulars
      1. PO
      1. USjvc
    2. COThe reason i'm trying to use neural network is that, as far as collaborative filtering is considered, we would need large amount of data rated by different users. Correct me if i'm wrong
      singulars
      1. PO
      1. USjvc
    3. COIt depends on your goal. Is this for commercial use, I would start with solutions such as pysuggest. For academic study of NNs or for personal learning I would start from the Salakhutdinov paper.
      singulars
      1. PO
      1. UScyborg
 

Querying!

 
Guidance
A row detail

Detail views are divided into sections. All the information in the data section comes from columns in the selected row. The other sections display data from other, related rows.

Related data can be related in a to-one or a to-many fashion. Captions of data related in a to-many fashion link to a list view showing a filtered view of the table.

Try moving around until you find a non-empty to-many entry and click on the label to get to one. You can move back to the root by clicking on the database name in the header.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload