Home       Trees       Indices       Help   
Topographica
Package topo :: Package learningfns :: Module som :: Class CFPLF_HebbianSOM
[hide private]
[frames] | no frames]

Class CFPLF_HebbianSOM

source code

                                  object --+            
                                           |            
base.parameterizedobject.ParameterizedObject --+        
                                               |        
                           base.cf.CFPLearningFn --+    
                                                   |    
                                           CFPLF_SOM --+
                                                       |
                                                      CFPLF_HebbianSOM

Hebbian learning rule for CFProjections to Self-Organizing Maps.

This implementation is obsolete and will be removed soon. Please see examples/cfsom_or.ty for current SOM support.



Nested Classes [hide private]

Inherited from base.parameterizedobject.ParameterizedObject: __metaclass__

Instance Methods [hide private]
 
__call__(self, iterator, input_activity, output_activity, learning_rate, **params) source code

Inherited from CFPLF_SOM: __init__

Inherited from base.cf.CFPLearningFn: constant_sum_connection_rate

Inherited from base.parameterizedobject.ParameterizedObject: __getstate__, __repr__, __setstate__, __str__, as_uninitialized, debug, defaults, force_new_dynamic_value, get_param_values, get_value_generator, inspect_value, message, print_param_values, script_repr, verbose, warning

Inherited from base.parameterizedobject.ParameterizedObject (private): _check_params, _instantiate_param, _set_name, _setup_params

Inherited from object: __delattr__, __getattribute__, __hash__, __new__, __reduce__, __reduce_ex__, __setattr__

Class Methods [hide private]

Inherited from base.parameterizedobject.ParameterizedObject: params, print_param_defaults

Class Variables [hide private]
  learning_radius = <topo.base.parameterclasses.Number object at...
The radius of the neighborhood function to be used for learning.
  crop_radius_multiplier = <topo.base.parameterclasses.Number ob...
Factor by which the radius should be multiplied, when deciding how far from the winner to keep updating the weights.
  neighborhood_kernel_generator = <topo.base.parameterclasses.Cl...
Neighborhood function

Inherited from base.parameterizedobject.ParameterizedObject: name, print_level

Properties [hide private]

Inherited from object: __class__

Method Details [hide private]

__call__(self, iterator, input_activity, output_activity, learning_rate, **params)
(Call operator)

source code 
Overrides: CFPLF_SOM.__call__

Class Variable Details [hide private]

learning_radius

The radius of the neighborhood function to be used for learning. Typically, this value will be set by the Sheet or Projection owning this CFPLearningFn, but it can also be set explicitly by the user.
Value:
Number(default= 0.0)

crop_radius_multiplier

Factor by which the radius should be multiplied, when deciding how far from the winner to keep updating the weights.
Value:
Number(default= 3.0, doc= """
        Factor by which the radius should be multiplied,
        when deciding how far from the winner to keep updating the weights.
        """)

neighborhood_kernel_generator

Neighborhood function
Value:
ClassSelectorParameter(PatternGenerator, default= Gaussian(x= 0.0, y= 0.0, aspect_\
ratio= 1.0), doc= "Neighborhood function")

   Home       Trees       Indices       Help   
Topographica
Generated by Epydoc 3.0beta1 on Thu Feb 21 15:25:05 2008 http://epydoc.sourceforge.net