Loading TOC...

cntk:selu

cntk:selu(
   $x as cntk:variable,
   [$scale as cntk:double],
   [$alpha as cntk:double],
   [$name as xs:string]
) as cntk:function

Summary

Scaled exponential linear unit operation. Computes the element-wise exponential linear of x: scale * x for x >= 0 and x: scale * alpha * (exp(x)-1) otherwise. The output tensor has the same shape as x.

Parameters
$x Any Function that outputs a tensor.
$scale The scale of the above equation.
$alpha The alpha of the above equation.
$name The name of the function instance in the network.

Example

  let $input-variable1 := cntk:input-variable(cntk:shape((3)), "float",
    fn:false(), fn:false(), "feature")
  let $input-variable2 := cntk:input-variable(cntk:shape((3)), "float",
    fn:false(), fn:false(), "feature")
  return cntk:selu($input-variable2, -8689658208.838396, -1894919915.011511, "m\Fe5?>_d")
  => cntk:function(Composite SELU (Input(Name(feature), Shape([3]),
  Dynamic Axes([Sequence Axis(Default Dynamic Axis), Batch Axis(Default Batch Axis)]))))

Stack Overflow iconStack Overflow: Get the most useful answers to questions from the MarkLogic community, or ask your own question.