---

annie Namespace Reference

Compounds
class	annie::CenterNeuron
class	annie::Exception
class	annie::File
class	annie::HopfieldNetwork
class	annie::InputLayer
class	annie::InputNeuron
class	annie::Layer
class	annie::Link
class	annie::Matrix
class	annie::MultiLayerNetwork
class	annie::Network
class	annie::Neuron
class	annie::RadialBasisNetwork
class	annie::RecurrentNeuron
class	annie::SimpleNeuron
class	annie::TrainingSet
class	annie::TwoLayerNetwork
Typedefs
typedef double	real
	Use this instead of double/float for real numbers pertaining to annie. More...
typedef std::vector< real >	VECTOR
	A vector of real numbers. More...
typedef real(*	ActivationFunction )(real)
	Activation functions take in a single real value and return a single real value. More...
typedef std::vector< Link * >	LINKS
	A set of Links, ie, weighted connections between two neurons. More...
Functions
real	isPositive (real x)
real	identity (real x)
	The identity function, ie, f(x) = x. More...
real	didentity (real x)
	Derivative of the identity function, thus always returns 1. More...
real	sigmoid (real x)
	Sigmoidal activation f(x). More...
real	dsigmoid (real x)
	Derivative of the sigmoidal function. More...
real	gaussian (real x)
	The guassian function. Sigma is taken to be 1.0. More...
real	dgaussian (real x)
	Derivative of the gaussian function (sigma is taken to be 1.0). More...
real	signum (real x)
real	tansig (real x)
	The tansig activation function. Courtesy Jose Ramos (warta@users.sourceforge.net). More...
real	dtansig (real x)
	Derivative of the tansign activation function. Courtesy Jose Ramos (warta@users.sourceforge.net). More...
real	random ()
	Generates a random real number between -1.0 and 1.0. More...
real	random2 ()
	Generates a random real number between 0.0 and 1.0. More...
int	randomInt (int low, int high)
Variables
const int	BINARY_FILE = 0
const int	TEXT_FILE = 1

---

Typedef Documentation

typedef real(* annie::ActivationFunction)(real)

Activation functions take in a single real value and return a single real value. These functions are used as activation functions of the neurons, i.e., the function applied to the raw output of the neurons. See also: identity , sigmoid , gaussian

typedef std::vector<Link *> annie::LINKS

A set of Links, ie, weighted connections between two neurons.

typedef double annie::real

Use this instead of double/float for real numbers pertaining to annie.

typedef std::vector<real> annie::VECTOR

A vector of real numbers.

---

Function Documentation

real dgaussian (  real    x )

Derivative of the gaussian function (sigma is taken to be 1.0).

real didentity (  real    x )

Derivative of the identity function, thus always returns 1.

real dsigmoid (  real    x )

Derivative of the sigmoidal function.

real dtansig (  real    x )

Derivative of the tansign activation function. Courtesy Jose Ramos (warta@users.sourceforge.net).

real gaussian (  real    x )

The guassian function. Sigma is taken to be 1.0.

real identity (  real    x )

The identity function, ie, f(x) = x.

real isPositive (  real    x )

Similar to the signum function, but used for non-bipolar Hopfield networks. Parameters: x  A real value Returns: 0 if x<=0, 1 otherwise.

real random (    )

Generates a random real number between -1.0 and 1.0.

real random2 (    )

Generates a random real number between 0.0 and 1.0.

int randomInt (  int    low, int    high )

Generates a random integer between given bounds. Parameters: low  Lower bound high  Upper bound Returns: A random integer i, low<=i<high

real sigmoid (  real    x )

Sigmoidal activation f(x).

real signum (  real    x )

Signum function Returns real instead of int because this function can be used as an activation function too, so wanted to keep the signature the same as other activation functions. Parameters: x  Real value as input Returns: -1 if x<0, +1 if x>=0

real tansig (  real    x )

The tansig activation function. Courtesy Jose Ramos (warta@users.sourceforge.net).

---

Variable Documentation

const int annie::BINARY_FILE = 0

The TrainingSet can be saved as a binary file or a text file, the latter allowing users to create a training set without using annie. A binary file is referred to as annie::BINARY_FILE and a text file as annie::TEXT_FILE See also: TrainingSet , TrainingSet::save , TEXT_FILE

const int annie::TEXT_FILE = 1

See also: BINARY_FILE

---