BNNSActivationFunctionLinearWithBias
An activation function that returns its input multiplied by a scale and added to a bias.
Declaration
var BNNSActivationFunctionLinearWithBias: BNNSActivationFunction { get }Discussion
This constant defines an activation function that returns values using the following operation:
alpha*x + betaThe following illustrates the output that the activation function generates from inputs in the range -10...10, an alpha of 2.0, and a beta of 10.0:
[Image]
See Also
Raw Values
init(_:)init(rawValue:)rawValueBNNSActivationFunctionAbsBNNSActivationFunctionCELUBNNSActivationFunctionClampedLeakyRectifiedLinearBNNSActivationFunctionELUBNNSActivationFunctionErfBNNSActivationFunctionGELUBNNSActivationFunctionGELUApproximationBNNSActivationFunctionGELUApproximation2BNNSActivationFunctionGELUApproximationSigmoidBNNSActivationFunctionGumbelBNNSActivationFunctionGumbelMaxBNNSActivationFunctionHardShrink