ParametrizedNeuron Class Reference

Neuron with a parametrized activation function. More...

#include <ParametrizedNeuron.h>

Inheritance diagram for ParametrizedNeuron:

[legend]Collaboration diagram for ParametrizedNeuron:

[legend]List of all members.

Public Member Functions
	ParametrizedNeuron (int label, real initialParameter=1.0, bool hasBias=true)
	Creates a simple neuron with the given label.
virtual void	setDesiredOutput (real desired)
	Sets the desired output of the neuron.
virtual const char *	getClassName ()
	Returns "ParametrizedNeuron".
Protected Member Functions
virtual void	_recacheOutput ()
	Neuron::_recacheOutput.
virtual void	_recacheError ()
	Neuron::_recacheError.
Protected Attributes
ParametrizedActivationFunction	_dParametrizedActivationFunction
	The derivative of the activation function, required for gradient descent training.
real	_parameter
	Current parameter of the activation function XXX: setParameter ??

---

Detailed Description

Neuron with a parametrized activation function.

If the parameter is adaptive, the modification can lie in _recacheError, for example.

Status: untested

---

Constructor & Destructor Documentation

ParametrizedNeuron (  int  label, real  initialParameter = 1.0, bool  hasBias = true )

Creates a simple neuron with the given label. Parameters: label  The label to be given to the neuron hasBias  true if the neuron is allowed to have a bias, false otherwise. Default is true See also: removeBias

---

Member Function Documentation

virtual void _recacheError (   )  [protected, virtual]

Neuron::_recacheError.

virtual void _recacheOutput (   )  [protected, virtual]

Neuron::_recacheOutput.

virtual const char* getClassName (   )  [virtual]

Returns "ParametrizedNeuron". Reimplemented in GABNeuron.

virtual void setDesiredOutput (  real  desired  )  [virtual]

Sets the desired output of the neuron. Should be called only for output neurons, i.e., those whose output is not connected to anyone else. Setting the desired output at these neurons will form the basis of error backpropagation Parameters: desired  The desired output of this neuron Exceptions: Exception  if the neuron is not an output neuron Implements AbstractNeuron.

---

Member Data Documentation

ParametrizedActivationFunction _dParametrizedActivationFunction [protected]

The derivative of the activation function, required for gradient descent training.

real _parameter [protected]

Current parameter of the activation function XXX: setParameter ??

---

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

• ParametrizedNeuron.h

---