fnn_activation_nonlinear Module Reference

Module dedicated to the class nonlinearactivation. More...

Data Types
type	nonlinearactivation
	Base class for nonlinear activation functions. Do not instanciate. More...

Functions/Subroutines
type(nonlinearactivation) function, public	construct_nonlinear_activation (self_size, batch_size)
	Constructor for class nonlinearactivation. More...
subroutine	nonlinear_apply_tangent_linear (self, member, dz, dy)
	Implements nonlinearactivation::apply_tangent_linear. More...
subroutine	nonlinear_apply_adjoint (self, member, dy, dz)
	Implements nonlinearactivation::apply_adjoint. More...

Detailed Description

Module dedicated to the class nonlinearactivation.

Function/Subroutine Documentation

construct_nonlinear_activation()

type(nonlinearactivation) function, public fnn_activation_nonlinear::construct_nonlinear_activation	(	integer(ik), intent(in)	self_size,
		integer(ik), intent(in)	batch_size
	)

Constructor for class nonlinearactivation.

Parameters

[in]	self_size	The value for linearactivation::self_size.
[in]	batch_size	The value for linearactivation::batch_size.

Returns

The constructed activation function.

nonlinear_apply_adjoint()

subroutine fnn_activation_nonlinear::nonlinear_apply_adjoint ( class(nonlinearactivation), intent(in)  self, integer(ik), intent(in)  member, real(rk), dimension(:), intent(in)  dy, real(rk), dimension(:), intent(out)  dz  )

private

Implements nonlinearactivation::apply_adjoint.

Applies the adjoint of the activation function.

The adjoint operator reads

Note

In principle, this method should only be called after linearactivation::apply_forward, where the linearisation is computed.

Parameters

[in]	self	The activation function.
[in]	member	The index inside the batch.
[in]	dy	The input of the adjoint operator.
[out]	dz	The output of the adjoint operator.

nonlinear_apply_tangent_linear()

subroutine fnn_activation_nonlinear::nonlinear_apply_tangent_linear ( class(nonlinearactivation), intent(in)  self, integer(ik), intent(in)  member, real(rk), dimension(:), intent(in)  dz, real(rk), dimension(:), intent(out)  dy  )

private

Implements nonlinearactivation::apply_tangent_linear.

Applies the TL of the activation function.

The TL operator reads

Note

In principle, this method should only be called after linearactivation::apply_forward, where the linearisation is computed.

Parameters

[in]	self	The activation function.
[in]	member	The index inside the batch.
[in]	dz	The input of the TL operator.
[out]	dy	The output of the TL operator.