ebl::convolution_module_2D Class Reference

#include <EblBasic.h>

Inheritance diagram for ebl::convolution_module_2D:

List of all members.

Public Member Functions
	convolution_module_2D (parameter &p, intg kerneli, intg kernelj, intg stridei, intg stridej, Idx< intg > &table, intg thick)
virtual void	fprop (state_idx &in, state_idx &out)
	forward propagation from in to out
virtual void	bprop (state_idx &in, state_idx &out)
	backward propagation from out to in
virtual void	bbprop (state_idx &in, state_idx &out)
	second-derivative backward propagation from out to in
virtual void	forget (forget_param_linear &fp)
	forgetting weights by replacing with random values
virtual int	replicable_order ()
	order of operation
virtual void	resize_output (state_idx &in, state_idx &out)
	resize the output based on input dimensions
Public Attributes
state_idx	kernel
intg	thickness
intg	stridei
intg	stridej
Idx< intg > &	table
	the table of connections between input and output

---

Detailed Description

This module applies 2D convolutions on dimensions 1 and 2 (0 contains different layers of information). This module has a replicable order of 3, if the input has a bigger order, use the replicable version of this module: convolution_module_2D_replicable.

---

Constructor & Destructor Documentation

ebl::convolution_module_2D::convolution_module_2D	(	parameter &	p,
		intg	kerneli,
		intg	kernelj,
		intg	stridei,
		intg	stridej,
		Idx< intg > &	table,
		intg	thick
	)

Constructor.

Parameters:

p

is used to store all parametric variables in a single place.

---

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

• /media/e/eblearn-trunk/libeblearn/include/EblBasic.h
• /media/e/eblearn-trunk/libeblearn/src/EblBasic.cpp