Loading TOC...


   $x as cntk:variable,
   [$mean as xs:double],
   [$seed as xs:unsignedLong],
   [$name as xs:string]
) as cntk:function


Create an instance of a Bernoulli random operation. This produces random numbers with the shape and dynamic axes specified by the operand, distributed according to the Bernoulli distribution with the specified success probability

$x Cntk variable (input, output, parameter, or constant) from which to copy the shape, data type, and dynamic axes.
$mean Success probability.
$seed Pseudo random number generator seed (default: automatically select a unique seed).
$name The name of the function instance in the network.


  let $input-variable1 := cntk:input-variable(cntk:shape((3)), "float",
    fn:false(), fn:false(), "feature")
  return cntk:bernoulli-random-like($input-variable1, .9284769431975840,
    1570816857518222944, "JwLhit")
  => cntk:function(Composite RandomDistribution (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.