# margin

Find classification margins for support vector machine (SVM) classifier

## Description

returns the classification
margins (`m`

= margin(`SVMModel`

,`Tbl`

,`ResponseVarName`

)`m`

) for the trained support vector
machine (SVM) classifier `SVMModel`

using the sample data in
table `Tbl`

and the class labels in
`Tbl.ResponseVarName`

.

`m`

is returned as a numeric vector with the same length as
`Y`

. The software estimates each entry of
`m`

using the trained SVM classifier
`SVMModel`

, the corresponding row of
`X`

, and the true class label
`Y`

.

## Examples

## Input Arguments

## More About

## Algorithms

For binary classification, the software defines the margin for
observation *j*, *m _{j}*, as

$${m}_{j}=2{y}_{j}f({x}_{j}),$$

where *y _{j}* ∊ {-1,1}, and

*f*(

*x*) is the predicted score of observation

_{j}*j*for the positive class. However,

*m*=

_{j}*y*

_{j}*f*(

*x*) is commonly used to define the margin.

_{j}## References

[1] Christianini, N., and J. C. Shawe-Taylor. *An
Introduction to Support Vector Machines and Other Kernel-Based Learning
Methods*. Cambridge, UK: Cambridge University Press, 2000.

## Extended Capabilities

## Version History

**Introduced in R2014a**

## See Also

`ClassificationSVM`

| `CompactClassificationSVM`

| `loss`

| `predict`

| `edge`

| `fitcsvm`