Editing Generative model (section)

==Contrast with discriminative classifiers==
A generative algorithm models how the data was generated in order to categorize a signal. It asks the question: based on my generation assumptions, which category is most likely to generate this signal? A discriminative algorithm does not care about how the data was generated, it simply categorizes a given signal. So, discriminative algorithms try to learn <math>p(y|x)</math> directly from the data and then try to classify data. On the other hand, generative algorithms try to learn <math>p(x,y)</math> which can be transformed into <math>p(y|x)</math> later to classify the data. One of the advantages of generative algorithms is that you can use <math>p(x,y)</math> to generate new data similar to existing data. On the other hand, it has been proved that some discriminative algorithms give better performance than some generative algorithms in classification tasks.<ref>{{harvnb|Ng|Jordan|2002}}</ref>

Despite the fact that discriminative models do not need to model the distribution of the observed variables, they cannot generally express complex relationships between the observed and target variables. But in general, they don't necessarily perform better than generative models at [[Classification (machine learning)|classification]] and [[Regression analysis|regression]] tasks. The two classes are seen as complementary or as different views of the same procedure.<ref>{{citation|editor-first=J. M. |editor-last=Bernardo|title=Bayesian statistics 8: proceedings of the eighth Valencia International Meeting, June 2-6, 2006|url={{google books |plainurl=y |id=Vh7vAAAAMAAJ|page=3}}|date=24 September 2007|publisher=Oxford University Press|isbn=978-0-19-921465-5|first1=C. M. |last1=Bishop |first2=J. |last2=Lasserre |contribution=Generative or Discriminative? getting the best of both worlds |pages=3–23}}</ref>