ScaledSigmoidFunction Class Reference

ScaledSigmoid Function. More...

Inheritance diagram for ScaledSigmoidFunction:

[legend]Collaboration diagram for ScaledSigmoidFunction:

[legend]List of all members.

Constructors
	ScaledSigmoidFunction (Real l=1.0, Real min=-1.0, Real max=+1.0)
	ScaledSigmoidFunction (PropertySettings &prop)
virtual	~ScaledSigmoidFunction ()
Interface
bool	setLambda (const Variant &v)
Variant	getLambda ()
bool	setMin (const Variant &v)
Variant	getMin ()
bool	setMax (const Variant &v)
Variant	getMax ()
virtual void	apply (RealVec &inputs, RealVec &outputs)
virtual void	derivate (const RealVec &x, const RealVec &y, RealVec &d) const
virtual ScaledSigmoidFunction *	clone () const
Public Attributes
Real	lambda
Real	min
Real	max

---

Detailed Description

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

Properties
Name	Type [isVector]	Access mode	Description	Class
typename	string	read-only	Class's type	Propertized
lambda	Real	read/write	function's slope	this
min	Real	read/write	function's minimun value	this
max	Real	read/write	function's maximun value	this

---

Constructor & Destructor Documentation

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

Construct a scaled sigmoid updater with parameter l

ScaledSigmoidFunction

(

PropertySettings &

prop

)

Construct

virtual ~ScaledSigmoidFunction

(

)

[inline, virtual]

Destructor

---

Member Function Documentation

bool setLambda

(

const Variant &

v

)

Set the slope of ScaledSigmoidFunction

Variant getLambda

(

)

Return the slope of ScaledSigmoidFunction

bool setMin

(

const Variant &

v

)

Set the minimum value of ScaledSigmoidFunction

Variant getMin

(

)

Return the minimum value of ScaledSigmoidFunction

bool setMax

(

const Variant &

v

)

Set the maximum value of ScaledSigmoidFunction

Variant getMax

(

)

Return the maximum value of ScaledSigmoidFunction

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

Implement the updating method

Reimplemented from OutputFunction.

virtual void derivate	(	const RealVec &	x,
		const RealVec &	y,
		RealVec &	d
	)			const [virtual]

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

Reimplemented from DerivableOutputFunction.

virtual ScaledSigmoidFunction* clone

(

)

const [virtual]

Clone this object

Reimplemented from OutputFunction.

---

Member Data Documentation

Real lambda

lambda is the slope of the curve

Real min

min is the y value when x -> -infinite

Real max

max is the y value when x -> +infinite

---

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

• include/liboutputfunctions.h

Copyright © 2005-2008 G. Massera

Contact: emmegian (at) yahoo (dot) it

  Documentation generated by