23,307

edits
# Changes

no edit summary

<span id="Regression"></span>

=Regression=

[[FILE:Linear regression.svg|border|right|thumb|300px|[https://en.wikipedia.org/wiki/Linear_regression Linear Regression] <ref>Random data points and their [https://en.wikipedia.org/wiki/Linear_regression linear regression]. [https://commons.wikimedia.org/wiki/File:Linear_regression.svg Created] with [https://en.wikipedia.org/wiki/Sage_%28mathematics_software%29 Sage] by Sewaqu, November 5, 2010, [https://en.wikipedia.org/wiki/Wikimedia_Commons Wikimedia Commons]</ref> ]]

[https://en.wikipedia.org/wiki/Regression_analysis Regression analysis] is a [https://en.wikipedia.org/wiki/Statistics statistical process] with a substantial overlap with machine learning to [https://en.wikipedia.org/wiki/Prediction predict] the value of an [https://en.wikipedia.org/wiki/Dependent_and_independent_variables Y variable] (output), given known value pairs of the X and Y variables. While [https://en.wikipedia.org/wiki/Linear_regression linear regression] deals with continuous outputs, [https://en.wikipedia.org/wiki/Logistic_regression logistic regression] covers binary or discrete output, such as win/loss, or win/draw/loss. Parameter estimation in regression analysis can be formulated as the [https://en.wikipedia.org/wiki/Mathematical_optimization minimization] of a [https://en.wikipedia.org/wiki/Loss_function cost or loss function] over a [https://en.wikipedia.org/wiki/Training_set training set] <ref>[https://en.wikipedia.org/wiki/Loss_function#Use_in_statistics Loss function - Use in statistics - Wkipedia]</ref>, such as [https://en.wikipedia.org/wiki/Mean_squared_error mean squared error] or [https://en.wikipedia.org/wiki/Cross_entropy#Cross-entropy_error_function_and_logistic_regression cross-entropy error function] for [https://en.wikipedia.org/wiki/Binary_classification binary classification] <ref>"Using [https://en.wikipedia.org/wiki/Cross_entropy#Cross-entropy_error_function_and_logistic_regression cross-entropy error function] instead of [https://en.wikipedia.org/wiki/Mean_squared_error sum of squares] leads to faster training and improved generalization", from [https://en.wikipedia.org/wiki/Sargur_Srihari Sargur Srihari], [http://www.cedar.buffalo.edu/~srihari/CSE574/Chap5/Chap5.2-Training.pdf Neural Network Training] (pdf)</ref>. The minimization is implemented by [[Iteration|iterative]] optimization [[Algorithms|algorithms]] or [https://en.wikipedia.org/wiki/Metaheuristic metaheuristics] such as [https://en.wikipedia.org/wiki/Iterated_local_search Iterated local search], [https://en.wikipedia.org/wiki/Gauss%E2%80%93Newton_algorithm Gauss–Newton algorithm], or [https://en.wikipedia.org/wiki/Conjugate_gradient_method conjugate gradient method].

<span id="LinearRegression"></span>

==Linear Regression==

<span id="LogisticRegression"></span>

==Logistic Regression==

==Instances==