Created LinearSVC/MultiLinearSVC classification (markdown)

LinearSVC-MultiLinearSVC-classification.md

@@ -0,0 +1,19 @@
+Golearn includes implementation with [liblinear](http://www.csie.ntu.edu.tw/~cjlin/liblinear/), which can be used for logistic regression and also linear support vector classification. It's best suited to datasets containing only a large number of numeric attributes, which often occur in natural language processing.
+
+## LinearSVC
+* The [LinearSVC](https://godoc.org/github.com/sjwhitworth/golearn/linear_models#LinearSVC) classifier outputs a binary class value (either 0 or 1). 
+* Only `FloatAttributes` are used as input.
+* Only one class Attribute is supported.
+* Training requires conversion of the dataset, which may cause memory presure (see issue #94). 
+* Prediction requires conversion of only the current row.
+* Penalty and loss parameters can be either "l1" or "l2". Not all combinations are supported.
+* The dual parameter decides whether liblinear optimises the primal or dual form, some choices are incompatible with combinations of "l1" and "l2".
+* C is roughly the "penalty" parameter. 
+* eps decides when to stop iterating. Smaller values typically take longer. 
+
+## MultiLinearSVC
+The [MultiLinearSVC](https://godoc.org/github.com/sjwhitworth/golearn/ensemble#MultiLinearSVC) can output a categorical class value, and uses the [OneVsAllModel](https://godoc.org/github.com/sjwhitworth/golearn/meta#OneVsAllModel) meta-classifier to output any CategoricalAttribute value. It works by training _n_ binary LinearSVC classifiers - one for each given class - and classifying a instance as a given class when one of the underlying LinearSVC classifiers reports 1. Parameters and other things are precisely the same as the LinearSVC.
+
+## Limitatations
+* Currently, per-class weights are unsupported.
+* Only `FloatAttributes` are currently supported.