#include <ebl_layers.h>

Inheritance diagram for ebl::subsampling_layer< T, Tstate >:

Public Member Functions
	subsampling_layer (parameter< T, Tstate > p, uint thickness, idxdim &kernel, idxdim &stride, bool tanh=true, const char name="subsampling_layer")
virtual	~subsampling_layer ()
	Destructor.
void	fprop (Tstate &in, Tstate &out)
	fprop from in to out
void	bprop (Tstate &in, Tstate &out)
	bprop
void	bbprop (Tstate &in, Tstate &out)
	bbprop
void	forget (forget_param_linear &fp)
	initialize the weights to random values
virtual fidxdim	fprop_size (fidxdim &i_size)
virtual fidxdim	bprop_size (const fidxdim &o_size)
virtual subsampling_layer< T, Tstate > *	copy ()
	Returns a deep copy of this module.
virtual std::string	describe ()
	Returns a string describing this module and its parameters.
Public Attributes
subsampling_module_replicable < T, Tstate >	subsampler
	subsampling
addc_module< T, Tstate >	adder
	bias vector
module_1_1< T, Tstate > *	sigmoid
	non-linear funct
Tstate *	sum
	subsampling result

Detailed Description

a subsampling neural net layer: subsampling + tanh non-linearity.

Constructor & Destructor Documentation

template<typename T , class Tstate >

ebl::subsampling_layer< T, Tstate >::subsampling_layer	(	parameter< T, Tstate > *	p,
		uint	thickness,
		idxdim &	kernel,
		idxdim &	stride,
		bool	tanh = `true`,
		const char *	name = `"subsampling_layer< T, Tstate >"`
	)

Constructor. Arguments are a pointer to a parameter in which the trainable weights will be appended, the number of inputs, and the number of outputs.

Parameters:

thickness	The number of features.
kernel	Size of subsampling kernel (without thickness).
strides	Strides of subsampling kernel (without thickness).
tanh	If true, use tanh squasher, stdsigmoid otherwise.

template<typename T , class Tstate >

fidxdim ebl::subsampling_layer< T, Tstate >::bprop_size ( const fidxdim & o_size ) [virtual]

Return dimensions compatible with this module given output dimensions. See module_1_1_gen's documentation for more details.

template<typename T , class Tstate >

fidxdim ebl::subsampling_layer< T, Tstate >::fprop_size ( fidxdim & i_size ) [virtual]

Return dimensions that are compatible with this module. See module_1_1_gen's documentation for more details.

The documentation for this class was generated from the following files: