This is the abstract basic network class - the training methods are in each subclass. More...

#include <math.h>
#include "netType.hpp"
#include "data.hpp"

Include dependency graph for net.hpp:

This graph shows which files directly or indirectly include this file:

Classes
class	Net
	The abstract network type upon which all others are based. It's not pure virtual, in that it encapsulates some high level operations (such as the top-level training algorithm). More...

struct	Net::SGDParams
	Training parameters for trainSGD(). This structure holds the parameters for the trainSGD() method, and serves as a better way of passing them than a long parameter list. All values have defaults set up by the constructor, which are given as constants. You can set parameters by hand, but there are fluent (chainable) setters for many members. More...

Detailed Description

This is the abstract basic network class - the training methods are in each subclass.

Definition in file net.hpp.

Function Documentation

double sigmoid ( double x )

inline

Logistic sigmoid function, which is our activation function

Definition at line 20 of file net.hpp.

double sigmoidDiff ( double x )

inline

The derivative of the sigmoid function

Definition at line 28 of file net.hpp.