Changes between Version 3 and Version 4 of MatrixFactorization


Ignore:
Timestamp:
05/06/11 18:47:49 (3 years ago)
Author:
MarinkaZitnik
Comment:

Legend:

Unmodified
Added
Removed
Modified
  • MatrixFactorization

    v3 v4  
    1111 
    1212=== nmf === 
    13 Standard NMF based on Kullbach Leibler divergence, simple multiplicative updates, enhanced to avoid numerical overflow [2]. [[BR]] 
     13Standard NMF based on Kullbach Leibler divergence, simple multiplicative updates, enhanced to avoid numerical overflow. [[BR]] 
    1414Reference: (Brunet, 2004). 
    1515 
     
    5959 
    6060 
    61 == Milestones == 
     61== Timeline == 
     62 
     63=== Milestone: MF 0.05 === 
    6264 
    6365'''April 20 -- May 23 (Before the official coding time)''' 
    6466 * To do some self coding to improve my further understanding of techniques. 
    65  * I will become absolutely clear about my future implementations, design and approaches I will follow. 
     67 * I will become absolutely clear about my future implementations, design and approaches I will follow.  
     68 * Discuss design and interface of scripting library to: integrate well with Orange framework, assure scalability for future added factorizations  
     69   or visualization support.  
     70 
     71---- 
     72 
     73=== Milestone: MF 0.1 === 
    6674 
    6775'''May 23 -- June 18 (Official coding period starts)''' 
    68  * Interface to perform all algorithms and combine them with initialization methods and extensions. 
     76 * Design and implement interface to perform all algorithms and combine them with initialization methods and extensions. 
    6977 * Implementing family of NMF techniques: NMF, nsNMF, lsNMF. 
    7078 
     79---- 
     80 
     81=== Milestone: MF 0.5 === 
     82 
    7183'''June 18 -- July 5''' 
    72  * Implementing family of NMF techniques: sNMF, lNMF, NNMA. 
     84 * Implementing family of NMF techniques: sNMF, lNMF, NNMA, PMF. 
    7385 
    7486'''July 5 -- July 15''' 
     
    7688 * Provide factorization quality measures: measure based on cophenetic correlation coefficient, sparseness, dispersion, residuals.  
    7789 
    78 '''July 15th mid-term evaluation deadline''' 
     90---- 
     91 
     92=== Milestone: MF 1.0 === 
    7993 
    8094'''July 15 -- July 25''' 
    81  * Implement Bayesian methods. Bayesian decomposition using Gibbs sampler, MCMC techniques such Bayesian factor regression modeling. 
     95 * Implement Bayesian methods. Bayesian decomposition using Gibbs sampler, MCMC techniques such Bayesian factor regression modeling (BD, BFRM). 
    8296 * Handling PMF on large, sparse and unbalanced datasets (algorithm for probabilistic sparse matrix factorization (PSMF)). 
    8397 
     
    93107 * A buffer for unpredictable delay. 
    94108 
    95 '''Redundant time''' 
     109---- 
     110 
     111=== Milestone: MF Future 1.1 === 
     112 
    96113 * Extend Bayesian methods (variational BD, linearly constrained BD). 
    97114 
    98 ''' August 26th final evaluation deadline''' 
     115---- 
    99116 
    100117== References ==  
    101  * Brunet, J. P., Tamayo, P., Golub, T. R., and Mesirov, J. P. Metagenes and molecular pattern discovery using matrix factorization. Proc Natl Acad Sci USA, 2004, 101(12), 4164--4169. 
     118 * Brunet, J. P., Tamayo, P., Golub, T. R., Mesirov, J. P. Metagenes and molecular pattern discovery using matrix factorization. Proc Natl Acad Sci USA, 2004, 101(12), 4164--4169. 
    102119 * Kim, H., Park, H. Sparse non-negative matrix factorizations via alternating non-negativity-constrained least squares for microarray data analysis. Bioinformatics (Oxford, England), 2007, 23(12), 1495--502. 
    103  * Pascual-Montano, A., Carazo, J. M., Kochi, K., Lehmann, D., and Pascual-Marqui, R. D. Nonsmooth nonnegative matrix factorization (nsnmf). IEEE transactions on pattern analysis and machine intelligence, 2006 28(3), 403--415. 
     120 * Pascual-Montano, A., Carazo, J. M., Kochi, K., Lehmann, D., Pascual-Marqui, R. D. Nonsmooth nonnegative matrix factorization (nsnmf). IEEE transactions on pattern analysis and machine intelligence, 2006 28(3), 403--415. 
    104121 * Wang, Y., Turk, M. Fisher non-negative matrix factorization for learning local features, 2004. 
    105122 * Salakhutdinov, R., Mnih, A. Probabilistic Matrix Factorization Learning, ICML, 2008. 
    106  * Sra, S.,Dhillon, I. S. Nonnegative Matrix Approximation : Algorithms and Applications. Sciences-New York, 2006, 1--36. 
     123 * Sra, S., Dhillon, I. S. Nonnegative Matrix Approximation : Algorithms and Applications. Sciences-New York, 2006, 1--36. 
    107124 * Zhiyong Shen, Liang Du, Xukun Shen, Yidong Shen, Interval-valued Matrix Factorization with Applications, Data Mining, IEEE International Conference on, pp. 1037--1042, 2010 IEEE International Conference on Data Mining, 2010. 
    108125 * Dueck, D., Morris, Q. D., Frey, B. J. Multi-way clustering of microarray data using probabilistic sparse matrix factorization. Bioinformatics (Oxford, England), 21 Suppl 1, 2005, 144--51. 
    109126 * Schmidt, M. N., Winther, O., Kai Hansen, L. Bayesian non-negative matrix factorization. Bayesian Statistics 7 (Oxford), 2003. 
    110  * Ochs, M. F.,Kossenkov A. V. NIH Public Access. Methods, Methods Enzymol., 2009, 59--77. 
     127 * Ochs, M. F., Kossenkov A. V. NIH Public Access. Methods, Methods Enzymol., 2009, 59--77.