Class CFPLF_HebbianSOM

source code

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This implementation is obsolete and will be removed soon.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 param.parameterized.Parameterized: __metaclass__

Instance Methods

[hide private]

__call__(self, iterator, input_activity, output_activity, learning_rate, **params)
Apply this learning function to the given set of ConnectionFields, and input and output activities, using the given learning_rate.

source code

Inherited from CFPLF_SOM: __init__

Inherited from base.cf.CFPLearningFn: constant_sum_connection_rate

Inherited from param.parameterized.Parameterized: __getstate__, __repr__, __setstate__, __str__, debug, defaults, force_new_dynamic_value, get_param_values, get_value_generator, inspect_value, message, print_param_values, script_repr, set_default, set_dynamic_time_fn, set_param, state_pop, state_push, verbose, warning

Inherited from param.parameterized.Parameterized (private): _add_parameter, _instantiate_param, _set_name, _setup_params

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

Class Methods

[hide private]

Inherited from param.parameterized.Parameterized: params, print_param_defaults

Class Variables

[hide private]

learning_radius = param.Number(default= 0.0)
The radius of the neighborhood function to be used for learning.

crop_radius_multiplier = param.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 = param.ClassSelector(PatternGen...
Neighborhood function

name = <param.parameterized.String object at 0xb26fb2c>
String identifier for this object.

Inherited from param.parameterized.Parameterized: 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

Apply this learning function to the given set of ConnectionFields, and input and output activities, using the given learning_rate.

Overrides: base.cf.CFPLearningFn.__call__: (inherited documentation)

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:

param.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:

param.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:

param.ClassSelector(PatternGenerator, default= Gaussian(x= 0.0, y= 0.0, aspect_rat
io= 1.0), doc= "Neighborhood function")

Class CFPLF_HebbianSOM

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

learning_radius

crop_radius_multiplier

neighborhood_kernel_generator

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