Loading TOC...

cntk.denseLayer

cntk.denseLayer(
   $operand as cntk.variable,
   $addition-parameters as Object
) as cntk.function

Summary

The creates a dense layer and apply it to operand. A dense layer is a fully connected layer of the form y = Wx + b, where x is the input, y is the output, W is the weight, and b is the bias.;

Parameters
$operand The operand of the operation.
$addition-parameters

"output-shape": cntk:shape. The shape of the output of this layer.

"activation": xs:string. Default: "identity". The optional activation to apply at the end.

"init": xs:double, or cntk:value, or cntk:initializer. Default: cntk:glorot-uniform-initializer(). Initial value of weights W.

"input-rank": xs:integer. Number of inferred axes to add to W (map-rank must not be given).

"map-rank": xs:integer. Expand W to leave exactly map-rank axes (input-rank must not be given).

"bias": xs:boolean. Default: true. If set to false, the layer will have no bias.

"bias-init": xs:double, or cntk:initializer. Default: 0. Initial value of bias.

"name": xs:string. Default: ""

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