---

annie::SimpleNeuron Class Reference

#include <SimpleNeuron.h>

Inheritance diagram for annie::SimpleNeuron:

List of all members.

Public Methods
	SimpleNeuron (int label, bool hasBias=true)
virtual void	setBias (real bias)
virtual bool	hasBias ()
	Is the neuron allowed to have a bias? More...
virtual real	getBias ()
	The bias of the neuron, 0.0 if it's not allowed to have a bias. More...
virtual void	removeBias ()
	Sets bias to 0.0 and prevents the neuron from having a bias. More...
virtual void	setDesiredOutput (real desired)
virtual void	setActivationFunction (ActivationFunction f, ActivationFunction df)
virtual void	connect (Neuron *from)
virtual void	connect (Neuron *from, real weight)
virtual void	calculateNewWeights (real learningRate, real momentum=0.0)
virtual void	update ()
virtual std::string	toString ()
	See also: Neuron::toString. More...
virtual const char *	getClassName ()
	Returns "SimpleNeuron". More...
virtual real	getWeight (Neuron *from)
Protected Methods
virtual void	_recacheOutput ()
	See also: Neuron::_recacheOutput. More...
virtual void	_recacheError ()
	See also: Neuron::_recacheError. More...
Protected Attributes
bool	_hasBias
	Is this neuron allowed to have a bias? More...
real	_bias
	If allowed to have a bias then the bias, otherwise 0.0. More...
real	_deltaBias
	The change in bias, calculated using the gradient descent rule. More...
ActivationFunction	_dActivationFunction
	The derivative of the activation function, required for gradient descent training. More...

---

Detailed Description

A simple perceptron - i.e., it takes as input the weighted sum of the outputs of the neurons connected to it. Probably the first type of neuron you would come across in any introductory literature of neural networks.

---

Constructor & Destructor Documentation

annie::SimpleNeuron::SimpleNeuron (  int    label, 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 annie::SimpleNeuron::_recacheError (    )  [protected, virtual]

See also: Neuron::_recacheError. Implements annie::Neuron.

virtual void annie::SimpleNeuron::_recacheOutput (    )  [protected, virtual]

See also: Neuron::_recacheOutput. Implements annie::Neuron. Reimplemented in annie::RecurrentNeuron.

virtual void annie::SimpleNeuron::calculateNewWeights (  real    learningRate, real    momentum = 0.0 )  [virtual]

Calculates the adjustment to incoming weights based on the gradient descent rule (backpropagation). Doesn't actually update the weights, just sets the value. See also: update

virtual void annie::SimpleNeuron::connect (  Neuron *    from, real    weight )  [virtual]

Connects the given neuron to this one, i.e., the output of the supplied neuron will be given as input to this neuron. The weight of the link will be the one supplied. Parameters: from  The neuron whose output is to be taken as input weight  The weight of the connection

virtual void annie::SimpleNeuron::connect (  Neuron *    from )  [virtual]

Connects the given neuron to this one, i.e., the output of the supplied neuron will be given as input to this neuron. A random weight is provided to the link Parameters: from  The neuron whose output is to be taken is as input

virtual real annie::SimpleNeuron::getBias (    )  [virtual]

The bias of the neuron, 0.0 if it's not allowed to have a bias.

virtual const char* annie::SimpleNeuron::getClassName (    )  [virtual]

Returns "SimpleNeuron". Implements annie::Neuron. Reimplemented in annie::RecurrentNeuron.

virtual real annie::SimpleNeuron::getWeight (  Neuron *    from )  [virtual]

Returns the weight of the link between the provided neuron and this neuron. Parameters: from  The neuron whose output is connected to this neuron's input Returns: The weight of the connection, 0.0 if no connection exists Reimplemented from annie::Neuron.

virtual bool annie::SimpleNeuron::hasBias (    )  [virtual]

Is the neuron allowed to have a bias?

virtual void annie::SimpleNeuron::removeBias (    )  [virtual]

Sets bias to 0.0 and prevents the neuron from having a bias.

virtual void annie::SimpleNeuron::setActivationFunction (  ActivationFunction    f, ActivationFunction    df )  [virtual]

Sets the activation function and its derivative (required for error backpropagation) Parameters: f  The activation function to be used df  The derivative of the activation function

virtual void annie::SimpleNeuron::setBias (  real    bias )  [virtual]

Sets the bias of the neuron. Parameters: bias  The bias to be given to the neuron Exceptions: Exception  if the neuron is not allowed to have a bias

virtual void annie::SimpleNeuron::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 Reimplemented in annie::RecurrentNeuron.

virtual std::string annie::SimpleNeuron::toString (    )  [virtual]

See also: Neuron::toString. Reimplemented from annie::Neuron.

virtual void annie::SimpleNeuron::update (    )  [virtual]

Updates the weights of incoming connections according to the values calculated using the gradient descent rule. See also: calculateNewWeights Reimplemented in annie::RecurrentNeuron.

---

Member Data Documentation

real annie::SimpleNeuron::_bias [protected]

If allowed to have a bias then the bias, otherwise 0.0.

ActivationFunction annie::SimpleNeuron::_dActivationFunction [protected]

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

real annie::SimpleNeuron::_deltaBias [protected]

The change in bias, calculated using the gradient descent rule.

bool annie::SimpleNeuron::_hasBias [protected]

Is this neuron allowed to have a bias?

---

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

• SimpleNeuron.h

---