neural_net::Classic_training_weight< Value_type, Iteration_type, Network_function_type, Space_function_type, Network_topology, Space_topology, Index_type > Class Template Reference

Template class for the generalize training functions that calculates generalized weight classical way. More...

#include <generalized_training_weight.hpp>

Inheritance diagram for neural_net::Classic_training_weight< Value_type, Iteration_type, Network_function_type, Space_function_type, Network_topology, Space_topology, Index_type >:

Inheritance graph
[legend]
Collaboration diagram for neural_net::Classic_training_weight< Value_type, Iteration_type, Network_function_type, Space_function_type, Network_topology, Space_topology, Index_type >:

Collaboration graph
[legend]

Public Member Functions

Data Fields


Detailed Description

template<typename Value_type, typename Iteration_type, typename Network_function_type, typename Space_function_type, typename Network_topology, typename Space_topology, typename Index_type>
class neural_net::Classic_training_weight< Value_type, Iteration_type, Network_function_type, Space_function_type, Network_topology, Space_topology, Index_type >

Template class for the generalize training functions that calculates generalized weight classical way.

Parameters:
Value_type is a type of values.
Iteration_type is a type of interation counter.
Network_function_type is a type of function that will return proper value based on network topology.
Space_funtion_type is a type of function that will return proper value based on space topology.
Network_topology is a type of function that computes distances between neurons based on network topology.
Space_topology is a type of function that computes distance between value and weight in proper topology.
Index_type is a type of index in the neural network container.

\[ y=n_f (n_t (c_1,c_2,v_1,v_2)) \cdot s_f (s_t (x,w)) \]


Constructor & Destructor Documentation

template<typename Value_type, typename Iteration_type, typename Network_function_type, typename Space_function_type, typename Network_topology, typename Space_topology, typename Index_type>
neural_net::Classic_training_weight< Value_type, Iteration_type, Network_function_type, Space_function_type, Network_topology, Space_topology, Index_type >::Classic_training_weight const Network_function_type &  n_f,
const Space_function_type &  s_f,
const Network_topology &  n_t,
const Space_topology &  s_t
throw () [inline]
 

Constructor.

Parameters:
n_f is a network functor.
s_f is a data space functor.
n_t is a network topology functor.
s_t is a space topology functor.

template<typename Value_type, typename Iteration_type, typename Network_function_type, typename Space_function_type, typename Network_topology, typename Space_topology, typename Index_type>
template<typename Value_type_2, typename Iteration_type_2, typename Network_function_type_2, typename Space_function_type_2, typename Network_topology_2, typename Space_topology_2, typename Index_type_2>
neural_net::Classic_training_weight< Value_type, Iteration_type, Network_function_type, Space_function_type, Network_topology, Space_topology, Index_type >::Classic_training_weight const Classic_training_weight< Value_type_2, Iteration_type_2, Network_function_type_2, Space_function_type_2, Network_topology_2, Space_topology_2, Index_type_2 > &  classic_training_weight  )  throw () [inline]
 

Copy constructor


Member Function Documentation

template<typename Value_type, typename Iteration_type, typename Network_function_type, typename Space_function_type, typename Network_topology, typename Space_topology, typename Index_type>
const Space_function_type::value_type neural_net::Classic_training_weight< Value_type, Iteration_type, Network_function_type, Space_function_type, Network_topology, Space_topology, Index_type >::operator() Value_type &  weight,
const Value_type &  value,
const Iteration_type &  iteration,
const Index_type &  c_1,
const Index_type &  c_2,
const Index_type &  v_1,
const Index_type &  v_2
throw () [inline]
 

Function computes generalized weight for training proces. This weight is not the same as weights in neural network.

Parameters:
weight is a weight from neural network.
value is a input value (value that trains network).
iteration is a number of training steps could be number of training data sample.
c_1 is a row number (position) in the network of the central neuron.
c_2 is a column number (position) in the network of the central neuron.
v_1 is a row number (position) in the network of the trained neuron.
v_2 is a column number (position) in the network of the trained neuron.

\[ y=n_f (n_t (c_1,c_2,v_1,v_2)) \cdot s_f (s_t (x,w)) \]

where x is value and w is neuron weight.


Field Documentation

template<typename Value_type, typename Iteration_type, typename Network_function_type, typename Space_function_type, typename Network_topology, typename Space_topology, typename Index_type>
Network_function_type neural_net::Classic_training_weight< Value_type, Iteration_type, Network_function_type, Space_function_type, Network_topology, Space_topology, Index_type >::network_function
 

Functor computes weight based on the result from network topology.

template<typename Value_type, typename Iteration_type, typename Network_function_type, typename Space_function_type, typename Network_topology, typename Space_topology, typename Index_type>
Network_topology neural_net::Classic_training_weight< Value_type, Iteration_type, Network_function_type, Space_function_type, Network_topology, Space_topology, Index_type >::network_topology
 

Functor computes generalized distance in network.

Reimplemented from neural_net::Basic_generalized_training_weight< Value_type, Iteration_type, Network_function_type, Space_function_type, Network_topology, Space_topology, Index_type >.

template<typename Value_type, typename Iteration_type, typename Network_function_type, typename Space_function_type, typename Network_topology, typename Space_topology, typename Index_type>
Space_function_type neural_net::Classic_training_weight< Value_type, Iteration_type, Network_function_type, Space_function_type, Network_topology, Space_topology, Index_type >::space_function
 

Functor computes weight based on the result from space topology.

template<typename Value_type, typename Iteration_type, typename Network_function_type, typename Space_function_type, typename Network_topology, typename Space_topology, typename Index_type>
Space_topology neural_net::Classic_training_weight< Value_type, Iteration_type, Network_function_type, Space_function_type, Network_topology, Space_topology, Index_type >::space_topology
 

Functor computes generalized distance in data space.

Reimplemented from neural_net::Basic_generalized_training_weight< Value_type, Iteration_type, Network_function_type, Space_function_type, Network_topology, Space_topology, Index_type >.


The documentation for this class was generated from the following file:
Generated on Wed Jun 28 14:39:54 2006 for Kohonen Neural Network Library Demo by  doxygen 1.4.6