Kohonen's Self Organizing Map

Float Neighboring Neuron

Constructors

FloatMappingNeuron(_prevs, _num_prev, _query_manager)

• _prevs(FloatUnitNeuron**)
  Array of memory addresses pointing to FloatUnitNeuron and its subclass instances
  Indicates previous neurons that the current neuron derives state data from
  If the assigned array consists of pointers to subclasses of FloatUnitNeuron, include (FloatUnitNeuron**) in front of the variable
• _num_prevs
  Number of elements (int) in the _prevs array
• _query_manager(FeedbackQueryManager*)
  Reference to the FeedbackQueryManager instance

FloatMappingNeuron(_prevs, _num_prev, _query_manager, _max)

• _prevs(FloatUnitNeuron**)
  Array of memory addresses pointing to FloatUnitNeuron and its subclass instances
  Indicates previous neurons that the current neuron derives state data from
  If the assigned array consists of pointers to subclasses of FloatUnitNeuron, include (FloatUnitNeuron**) in front of the variable
• _num_prevs
  Number of elements (int) in the _prevs array
• _query_manager
  Reference to the FeedbackQueryManager instance
• _max
  Largest amount of the initial weight values for each neuron

Structure

Public Methods and Variables

• lr(floating point value)
  Learning rate for weight update
  The default value is set to 0.7f
• void assign_neighbors(FloatMappingNeuron** _neighbors, int _num_neighbors)
  Assign neighboring neurons in the self organizing map
  _neighbors
  • Array of pointers to FloatMappingNeuron
  _num_neighbors
  • Number of elements in _neighbors
• void feedforward()
  Calculate distance between weights stored in neuron and the values of input neurons
• void feedback(float* fb_input)
  Update weights based on values of the input neurons and the distance calculated in feedforward()
  fb_input is a 2-D array that consists of {CURRENT_NUMBER_OF_NEIGHBORS, NUMBER_OF_NEIGHBORS_TO_UPDATE}
• float* see_memory()
  Output current weight values of the neuron

Additional Notes and Code

For more details on private variables, methods, and other functionalities performed within the definition of the class, refer to the hpp file and the cpp file .

Kohonen's SOM Operator

Subclass of GlobalOperator that starts the Kohonen's self organizing map training process of the neural network

Constructors

FloatKohonenSOM(_maps, int _num_maps, int _neighbor_range)

• _maps(FloatMappingNeuron**)
  Array of memory addresses to FloatMappingNeuron used as the output neurons
• _num_maps
  Number of elements (int) in _maps
• _neighbor_range
  Number of neighboring neurons to update starting with the winning neuron

Code

For more details on private variables, methods, and other functionalities performed within the definition of the class, refer to the hpp file and the cpp file .