ScaledSigmoidFunction Class Reference

ScaledSigmoid Function. More...

Inheritance diagram for ScaledSigmoidFunction:

List of all members.

Public Member Functions
	ScaledSigmoidFunction (double l=1.0, double min=-1.0, double max=+1.0)
	Construct a scaled sigmoid updater with parameter l.
virtual	~ScaledSigmoidFunction ()
	Destructor.
virtual void	apply (DoubleVector &inputs, DoubleVector &outputs)
	Implement the updating method.
virtual void	configure (ConfigurationParameters &params, QString prefix)
	Configures the object using a ConfigurationParameters object.
virtual bool	derivate (const DoubleVector &x, const DoubleVector &y, DoubleVector &d) const
	return the approximation commonly used in backpropagation learning: x(1-x)
virtual void	save (ConfigurationParameters &params, QString prefix)
	Save the actual status of parameters into the ConfigurationParameters object passed.
Public Attributes
double	lambda
	lambda is the slope of the curve
double	max
	max is the y value when x -> +infinite
double	min
	min is the y value when x -> -infinite

---

Detailed Description

ScaledSigmoid Function.

lambda is the slope of the curve
min is the y value when x -> -infinite
max is the y value when x -> +infinite
(max-min) is the y value when x == 0

Definition at line 224 of file liboutputfunctions.h.

---

Constructor & Destructor Documentation

ScaledSigmoidFunction	(	double	l = 1.0,
		double	min = -1.0,
		double	max = +1.0
	)

Construct a scaled sigmoid updater with parameter l.

Definition at line 211 of file liboutputfunctions.cpp.

References ScaledSigmoidFunction::lambda, ScaledSigmoidFunction::max, and ScaledSigmoidFunction::min.

virtual ~ScaledSigmoidFunction

(

)

[inline, virtual]

Destructor.

Definition at line 229 of file liboutputfunctions.h.

---

Member Function Documentation

void apply	(	DoubleVector &	inputs,
		DoubleVector &	outputs
	)		[virtual]

Implement the updating method.

Implements OutputFunction.

Definition at line 218 of file liboutputfunctions.cpp.

References farsa::exp(), farsa::inv(), ScaledSigmoidFunction::lambda, ScaledSigmoidFunction::max, ScaledSigmoidFunction::min, and farsa::mul().

void configure	(	ConfigurationParameters &	params,
		QString	prefix
	)		[virtual]

Configures the object using a ConfigurationParameters object.

Parameters:

params	the configuration parameters object with parameters to use
prefix	the prefix to use to access the object configuration parameters. This is guaranteed to end with the separator character when called by the factory, so you don't need to add one

Implements ParameterSettableWithConfigureFunction.

Definition at line 236 of file liboutputfunctions.cpp.

References ConfigurationParameters::getValue(), ScaledSigmoidFunction::lambda, ScaledSigmoidFunction::max, and ScaledSigmoidFunction::min.

bool derivate	(	const DoubleVector &	x,
		const DoubleVector &	y,
		DoubleVector &	d
	)		const [virtual]

return the approximation commonly used in backpropagation learning: x(1-x)

Reimplemented from OutputFunction.

Definition at line 228 of file liboutputfunctions.cpp.

References ScaledSigmoidFunction::lambda, and farsa::subtract().

void save	(	ConfigurationParameters &	params,
		QString	prefix
	)		[virtual]

Save the actual status of parameters into the ConfigurationParameters object passed.

Parameters:

params	the configuration parameters object on which save actual parameters
prefix	the prefix to use to access the object configuration parameters.

Implements ParameterSettable.

Definition at line 269 of file liboutputfunctions.cpp.

References ConfigurationParameters::createParameter(), ScaledSigmoidFunction::lambda, ScaledSigmoidFunction::max, ScaledSigmoidFunction::min, and ConfigurationParameters::startObjectParameters().

---

Member Data Documentation

double lambda

lambda is the slope of the curve

Definition at line 254 of file liboutputfunctions.h.

Referenced by ScaledSigmoidFunction::apply(), ScaledSigmoidFunction::configure(), ScaledSigmoidFunction::derivate(), ScaledSigmoidFunction::save(), and ScaledSigmoidFunction::ScaledSigmoidFunction().

double max

max is the y value when x -> +infinite

Definition at line 258 of file liboutputfunctions.h.

Referenced by ScaledSigmoidFunction::apply(), ScaledSigmoidFunction::configure(), ScaledSigmoidFunction::save(), and ScaledSigmoidFunction::ScaledSigmoidFunction().

double min

min is the y value when x -> -infinite

Definition at line 256 of file liboutputfunctions.h.

Referenced by ScaledSigmoidFunction::apply(), ScaledSigmoidFunction::configure(), ScaledSigmoidFunction::save(), and ScaledSigmoidFunction::ScaledSigmoidFunction().

---

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

• nnfw/include/liboutputfunctions.h
• nnfw/src/liboutputfunctions.cpp