Package topo :: Package base :: Module functionfamilies :: Class Hebbian

Class Hebbian

                             object --+        
                                      |        
parameterizedobject.ParameterizedObject --+    
                                          |    
                                 LearningFn --+
                                              |
                                             Hebbian

Basic Hebbian rule; Dayan and Abbott, 2001, equation 8.3.

Increases each weight in proportion to the product of this neuron's activity and the input activity.

Requires some form of output_fn normalization for stability.

Nested Classes

[hide private]

Inherited from parameterizedobject.ParameterizedObject: __metaclass__

Instance Methods

[hide private]

__call__(self, input_activity, unit_activity, weights, single_connection_learning_rate)
Apply this learning function given the input and output activities and current weights.

source code

Inherited from parameterizedobject.ParameterizedObject: __getstate__, __init__, __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 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 parameterizedobject.ParameterizedObject: params, print_param_defaults

Class Variables

[hide private]

Inherited from parameterizedobject.ParameterizedObject: name, print_level

Properties

[hide private]

Inherited from object: __class__

Method Details

[hide private]

call(self, input_activity, unit_activity, weights, single_connection_learning_rate)
(Call operator)

source code

Apply this learning function given the input and output activities and current weights.

Must be implemented by subclasses.

Overrides: LearningFn.__call__: (inherited documentation)

Class Hebbian

__call__(self, input_activity, unit_activity, weights, single_connection_learning_rate) (Call operator)

call(self, input_activity, unit_activity, weights, single_connection_learning_rate)
(Call operator)